Dr. Sakyasingha Dasgupta

Group(s): Neural Control and Robotics
Email:
sdasgup@gwdg.de

Global QuickSearch:   Matches: 0

Search Settings

    Author / Editor / Organization
    Year
    Title
    Journal / Proceedings / Book
    Dasgupta, S. (2014).
    Cognitive Aging as Interplay between Hebbian Learning and Criticality. ArXiv e-prints, 1 - 56.
    BibTeX:
    @article{dasgupta2014,
      author = {Dasgupta, S.},
      title = {Cognitive Aging as Interplay between Hebbian Learning and Criticality},
      pages = {1 - 56},
      journal = {ArXiv e-prints},
      year = {2014},
      month = {02},
      url = {http://adsabs.harvard.edu/abs/2014arXiv1402.0836D},
      abstract = {Cognitive ageing seems to be a story of global degradation. As one ages there are a number of physical, chemical and biological changes that take place. Therefore it is logical to assume that the brain is no exception to this phenomenon. The principle purpose of this project is to use models of neural dynamics and learning based on the underlying principle of self-organised criticality, to account for the age related cognitive effects. In this regard learning in neural networks can serve as a model for the acquisition of skills and knowledge in early development stages i.e. the ageing process and criticality in the network serves as the optimum state of cognitive abilities. Possible candidate mechanisms for ageing in a neural network are loss of connectivity and neurons, increase in the level of noise, reduction in white matter or more interestingly longer learning history and the competition among several optimization objectives. In this paper we are primarily interested in the affect of the longer learning history on memory and thus the optimality in the brain. Hence it is hypothesized that prolonged learning in the form of associative memory patterns can destroy the state of criticality in the network. We base our model on Tsodyks and Markrams 49 model of dynamic synapses, in the process to explore the effect of combining standard Hebbian learning with the phenomenon of Self-organised criticality. The project mainly consists of evaluations and simulations of networks of integrate and fire-neurons that have been subjected to various combinations of neural-level ageing effects, with the aim of establishing the primary hypothesis and understanding the decline of cognitive abilities due to ageing, using one of its important characteristics, a longer learning history.1}}
    Abstract: Cognitive ageing seems to be a story of global degradation. As one ages there are a number of physical, chemical and biological changes that take place. Therefore it is logical to assume that the brain is no exception to this phenomenon. The principle purpose of this project is to use models of neural dynamics and learning based on the underlying principle of self-organised criticality, to account for the age related cognitive effects. In this regard learning in neural networks can serve as a model for the acquisition of skills and knowledge in early development stages i.e. the ageing process and criticality in the network serves as the optimum state of cognitive abilities. Possible candidate mechanisms for ageing in a neural network are loss of connectivity and neurons, increase in the level of noise, reduction in white matter or more interestingly longer learning history and the competition among several optimization objectives. In this paper we are primarily interested in the affect of the longer learning history on memory and thus the optimality in the brain. Hence it is hypothesized that prolonged learning in the form of associative memory patterns can destroy the state of criticality in the network. We base our model on Tsodyks and Markrams 49 model of dynamic synapses, in the process to explore the effect of combining standard Hebbian learning with the phenomenon of Self-organised criticality. The project mainly consists of evaluations and simulations of networks of integrate and fire-neurons that have been subjected to various combinations of neural-level ageing effects, with the aim of establishing the primary hypothesis and understanding the decline of cognitive abilities due to ageing, using one of its important characteristics, a longer learning history.1
    Review:
    Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2013).
    Information dynamics based self-adaptive reservoir for delay temporal memory tasks. Evolving Systems, 235-249, 4, 4. DOI: 10.1007/s12530-013-9080-y.
    BibTeX:
    @article{dasguptawoergoettermanoonpong2013,
      author = {Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {Information dynamics based self-adaptive reservoir for delay temporal memory tasks},
      pages = {235-249},
      journal = {Evolving Systems},
      year = {2013},
      volume= {4},
      number = {4},
      publisher = {Springer Berlin Heidelberg},
      url = {http://dx.doi.org/10.1007/s12530-013-9080-y},
      doi = {10.1007/s12530-013-9080-y},
      abstract = {Recurrent neural networks of the reservoir computing (RC) type have been found useful in various time-series processing tasks with inherent non-linearity and requirements of variable temporal memory. Specifically for delayed response tasks involving the transient memorization of information (temporal memory), self-adaptation in RC is crucial for generalization to varying delays. In this work using information theory, we combine a generalized intrinsic plasticity rule with a local information dynamics based schema of reservoir neuron leak adaptation. This allows the RC network to be optimized in a self-adaptive manner with minimal parameter tuning. Local active information storage, measured as the degree of influence of previous activity on the next time step activity of a neuron, is used to modify its leak-rate. This results in RC network with non-uniform leak rate which depends on the time scales of the incoming input. Intrinsic plasticity (IP) is aimed at maximizing the mutual information between each neurons input and output while maintaining a mean level of activity (homeostasis). Experimental results on two standard benchmark tasks confirm the extended performance of this system as compared to the static RC (fixed leak and no IP) and RC with only IP. In addition, using both a simulated wheeled robot and a more complex physical hexapod robot, we demonstrate the ability of the system to achieve long temporal memory for solving a basic T-shaped maze navigation task with varying delay time scale.}}
    Abstract: Recurrent neural networks of the reservoir computing (RC) type have been found useful in various time-series processing tasks with inherent non-linearity and requirements of variable temporal memory. Specifically for delayed response tasks involving the transient memorization of information (temporal memory), self-adaptation in RC is crucial for generalization to varying delays. In this work using information theory, we combine a generalized intrinsic plasticity rule with a local information dynamics based schema of reservoir neuron leak adaptation. This allows the RC network to be optimized in a self-adaptive manner with minimal parameter tuning. Local active information storage, measured as the degree of influence of previous activity on the next time step activity of a neuron, is used to modify its leak-rate. This results in RC network with non-uniform leak rate which depends on the time scales of the incoming input. Intrinsic plasticity (IP) is aimed at maximizing the mutual information between each neurons input and output while maintaining a mean level of activity (homeostasis). Experimental results on two standard benchmark tasks confirm the extended performance of this system as compared to the static RC (fixed leak and no IP) and RC with only IP. In addition, using both a simulated wheeled robot and a more complex physical hexapod robot, we demonstrate the ability of the system to achieve long temporal memory for solving a basic T-shaped maze navigation task with varying delay time scale.
    Review:
    Dasgupta, S. and Wörgötter, F. and Morimoto, J. and Manoonpong, P. (2013).
    Neural Combinatorial Learning of Goal-directed Behavior with Reservoir Critic and Reward Modulated Hebbian Plasticity. IEEE International Conference on Systems, Man, and Cybernetics SMC, 993-1000. DOI: 10.1109/SMC.2013.174.
    BibTeX:
    @inproceedings{dasguptawoergoettermorimoto2013,
      author = {Dasgupta, S. and Wörgötter, F. and Morimoto, J. and Manoonpong, P.},
      title = {Neural Combinatorial Learning of Goal-directed Behavior with Reservoir Critic and Reward Modulated Hebbian Plasticity},
      pages = {993-1000},
      booktitle = {IEEE International Conference on Systems, Man, and Cybernetics SMC},
      year = {2013},
      location = {Manchester (UK)},
      month = {October 13-16},
      doi = {10.1109/SMC.2013.174},
      abstract = {Learning of goal-directed behaviors in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation-based learning) and operant conditioning (reward-based learning). Although traditionally modeled as separate learning systems in artificial agents, numerous animal experiments point towards their co-operative role in behavioral learning. Based on this concept, the recently introduced framework of neural combinatorial learning combines the two systems where both the systems run in parallel to guide the overall learned behavior. Such a combinatorial learning demonstrates a faster and efficient learner. In this work, we further improve the framework by applying a reservoir computing network (RC) as an adaptive critic unit and reward modulated Hebbian plasticity. Using a mobile robot system for goal-directed behavior learning, we clearly demonstrate that the reservoir critic outperforms traditional radial basis function (RBF) critics in terms of stability of convergence and learning time. Furthermore the temporal memory in RC allows the system to learn partially observable markov decision process scenario, in contrast to a memory less RBF critic.}}
    Abstract: Learning of goal-directed behaviors in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation-based learning) and operant conditioning (reward-based learning). Although traditionally modeled as separate learning systems in artificial agents, numerous animal experiments point towards their co-operative role in behavioral learning. Based on this concept, the recently introduced framework of neural combinatorial learning combines the two systems where both the systems run in parallel to guide the overall learned behavior. Such a combinatorial learning demonstrates a faster and efficient learner. In this work, we further improve the framework by applying a reservoir computing network (RC) as an adaptive critic unit and reward modulated Hebbian plasticity. Using a mobile robot system for goal-directed behavior learning, we clearly demonstrate that the reservoir critic outperforms traditional radial basis function (RBF) critics in terms of stability of convergence and learning time. Furthermore the temporal memory in RC allows the system to learn partially observable markov decision process scenario, in contrast to a memory less RBF critic.
    Review:
    Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2012).
    Information Theoretic Self-organised Adaptation in Reservoirs for Temporal Memory Tasks. Engineering Applications of Neural Networks, 31-40, 311. DOI: 10.1007/978-3-642-32909-8_4.
    BibTeX:
    @incollection{dasguptawoergoettermanoonpong2012,
      author = {Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {Information Theoretic Self-organised Adaptation in Reservoirs for Temporal Memory Tasks},
      pages = {31-40},
      booktitle = {Engineering Applications of Neural Networks},
      year = {2012},
      volume= {311},
      editor = {Jayne, Chrisina and Yue, Shigang and Iliadis, Lazaros},
      publisher = {Springer Berlin Heidelberg},
      series = {Communications},
      url = {http://dx.doi.org/10.1007/978-3-642-32909-8_4},
      doi = {10.1007/978-3-642-32909-8_4},
      abstract = {Recurrent neural networks of the Reservoir Computing (RC) type have been found useful in various time-series processing tasks with inherent non-linearity and requirements of temporal memory. Here with the aim to obtain extended temporal memory in generic delayed response tasks, we combine a generalised intrinsic plasticity mechanism with an information storage based neuron leak adaptation rule in a self-organised manner. This results in adaptation of neuron local memory in terms of leakage along with inherent homeostatic stability. Experimental results on two benchmark tasks confirm the extended performance of this system as compared to a static RC and RC with only intrinsic plasticity. Furthermore, we demonstrate the ability of the system to solve long temporal memory tasks via a simulated T-shaped maze navigation scenario.}}
    Abstract: Recurrent neural networks of the Reservoir Computing (RC) type have been found useful in various time-series processing tasks with inherent non-linearity and requirements of temporal memory. Here with the aim to obtain extended temporal memory in generic delayed response tasks, we combine a generalised intrinsic plasticity mechanism with an information storage based neuron leak adaptation rule in a self-organised manner. This results in adaptation of neuron local memory in terms of leakage along with inherent homeostatic stability. Experimental results on two benchmark tasks confirm the extended performance of this system as compared to a static RC and RC with only intrinsic plasticity. Furthermore, we demonstrate the ability of the system to solve long temporal memory tasks via a simulated T-shaped maze navigation scenario.
    Review:
    Ren, G. and Chen, W. and Kolodziejski, C. and Wörgötter, F. and Dasgupta, S. and Manoonpong, P. (2012).
    Multiple Chaotic Central Pattern Generators for Locomotion Generation and Leg Damage Compensation in a Hexapod Robot. IEEE/RSJ International Conference on Intelligent Robots and Systems IROS. DOI: 10.1109/IROS.2012.6385573.
    BibTeX:
    @inproceedings{renchenkolodziejski2012,
      author = {Ren, G. and Chen, W. and Kolodziejski, C. and Wörgötter, F. and Dasgupta, S. and Manoonpong, P.},
      title = {Multiple Chaotic Central Pattern Generators for Locomotion Generation and Leg Damage Compensation in a Hexapod Robot},
      booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems IROS},
      year = {2012},
      doi = {10.1109/IROS.2012.6385573},
      abstract = {In chaos control, an originally chaotic system is modified so that periodic dynamics arise. One application of this is to use the periodic dynamics of a single chaotic system as walking patterns in legged robots. In our previous work we applied such a controlled chaotic system as a central pattern generator (CPG) to generate different gait patterns of our hexapod robot AMOSII. However, if one or more legs break, its control fails. Specifically, in the scenario presented here, its movement permanently deviates from a desired trajectory. This is in contrast to the movement of real insects as they can compensate for body damages, for instance, by adjusting the remaining legs frequency. To achieve this for our hexapod robot, we extend the system from one chaotic system serving as a single CPG to multiple chaotic systems, performing as multiple CPGs. Without damage, the chaotic systems synchronize and their dynamics is identical (similar to a single CPG). With damage, they can lose synchronization leading to independent dynamics. In both simulations and real experiments, we can tune the oscillation frequency of every CPG manually so that the controller can indeed compensate for leg damage. In comparison to the trajectory of the robot controlled by only a single CPG, the trajectory produced by multiple chaotic CPG controllers resembles the original trajectory by far better. Thus, multiple chaotic systems that synchronize for normal behavior but can stay desynchronized in other circumstances are an effective way to control complex behaviors where, for instance, different body parts have to do independent movements like after leg damage.}}
    Abstract: In chaos control, an originally chaotic system is modified so that periodic dynamics arise. One application of this is to use the periodic dynamics of a single chaotic system as walking patterns in legged robots. In our previous work we applied such a controlled chaotic system as a central pattern generator (CPG) to generate different gait patterns of our hexapod robot AMOSII. However, if one or more legs break, its control fails. Specifically, in the scenario presented here, its movement permanently deviates from a desired trajectory. This is in contrast to the movement of real insects as they can compensate for body damages, for instance, by adjusting the remaining legs frequency. To achieve this for our hexapod robot, we extend the system from one chaotic system serving as a single CPG to multiple chaotic systems, performing as multiple CPGs. Without damage, the chaotic systems synchronize and their dynamics is identical (similar to a single CPG). With damage, they can lose synchronization leading to independent dynamics. In both simulations and real experiments, we can tune the oscillation frequency of every CPG manually so that the controller can indeed compensate for leg damage. In comparison to the trajectory of the robot controlled by only a single CPG, the trajectory produced by multiple chaotic CPG controllers resembles the original trajectory by far better. Thus, multiple chaotic systems that synchronize for normal behavior but can stay desynchronized in other circumstances are an effective way to control complex behaviors where, for instance, different body parts have to do independent movements like after leg damage.
    Review:
    Dasgupta, S. and Herrmann, J M. (2011).
    Critical dynamics in homeostatic memory networks. Computational and Systems Neuroscience Cosyne, Nature Precedings. DOI: 10.1038/npre.2011.5829.1.
    BibTeX:
    @inproceedings{dasguptaherrmann2011,
      author = {Dasgupta, S. and Herrmann, J M.},
      title = {Critical dynamics in homeostatic memory networks},
      booktitle = {Computational and Systems Neuroscience Cosyne, Nature Precedings},
      year = {2011},
      doi = {10.1038/npre.2011.5829.1},
      abstract = {Critical behavior in neural networks characterized by scale-free event distributions and brought about by self-regulatory mechanisms such as short-term synaptic dynamics or homeostatic plasticity, is believed to optimize sensitivity to input and information transfer in the system. Although theoretical predictions of the spike distributions have been confirmed by in-vitro experiments, in-vivo data yield a more complex picture which might be due to the in-homogeneity of the network structure, leakage in currents or massive driving inputs which has so far not been comprehensively covered by analytical or numerical studies.}}
    Abstract: Critical behavior in neural networks characterized by scale-free event distributions and brought about by self-regulatory mechanisms such as short-term synaptic dynamics or homeostatic plasticity, is believed to optimize sensitivity to input and information transfer in the system. Although theoretical predictions of the spike distributions have been confirmed by in-vitro experiments, in-vivo data yield a more complex picture which might be due to the in-homogeneity of the network structure, leakage in currents or massive driving inputs which has so far not been comprehensively covered by analytical or numerical studies.
    Review:
    Manoonpong, P. and Dasgupta, S. and Goldschmidt, D. and Wörgötter, F. (2014).
    Reservoir-based online adaptive forward models with neural control for complex locomotion in a hexapod robot. International Joint Conference on Neural Networks (IJCNN), 3295-3302. DOI: 10.1109/IJCNN.2014.6889405.
    BibTeX:
    @inproceedings{manoonpongdasguptagoldschmidt2014,
      author = {Manoonpong, P. and Dasgupta, S. and Goldschmidt, D. and Wörgötter, F.},
      title = {Reservoir-based online adaptive forward models with neural control for complex locomotion in a hexapod robot},
      pages = {3295-3302},
      booktitle = {International Joint Conference on Neural Networks (IJCNN)},
      year = {2014},
      month = {July},
      doi = {10.1109/IJCNN.2014.6889405},
      abstract = {Walking animals show fascinating locomotor abilities and complex behaviors. Biological study has revealed that such complex behaviors is a result of a combination of biomechanics and neural mechanisms. While biomechanics allows for flexibility and a variety of movements, neural mechanisms generate locomotion, make predictions, and provide adaptation. Inspired by this finding, we present here an artificial bio-inspired walking system which combines biomechanics (in terms of its body and leg structures) and neural mechanisms. The neural mechanisms consist of 1) central pattern generator-based control for generating basic rhythmic patterns and coordinated movements, 2) reservoir-based adaptive forward models with efference copies for sensory prediction as well as state estimation, and 3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Simulation results show that this bio-inspired approach allows the walking robot to perform complex locomotor abilities including walking on undulated terrains, crossing a large gap, as well as climbing over a high obstacle and a fleet of stairs.}}
    Abstract: Walking animals show fascinating locomotor abilities and complex behaviors. Biological study has revealed that such complex behaviors is a result of a combination of biomechanics and neural mechanisms. While biomechanics allows for flexibility and a variety of movements, neural mechanisms generate locomotion, make predictions, and provide adaptation. Inspired by this finding, we present here an artificial bio-inspired walking system which combines biomechanics (in terms of its body and leg structures) and neural mechanisms. The neural mechanisms consist of 1) central pattern generator-based control for generating basic rhythmic patterns and coordinated movements, 2) reservoir-based adaptive forward models with efference copies for sensory prediction as well as state estimation, and 3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Simulation results show that this bio-inspired approach allows the walking robot to perform complex locomotor abilities including walking on undulated terrains, crossing a large gap, as well as climbing over a high obstacle and a fleet of stairs.
    Review:
    Zeidan, B. and Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2014).
    Adaptive Landmark-Based Navigation System Using Learning Techniques. From Animals to Animats 13, 121-131, 8575. DOI: 10.1007/978-3-319-08864-8_12.
    BibTeX:
    @inproceedings{zeidandasguptawoergoetter2014,
      author = {Zeidan, B. and Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {Adaptive Landmark-Based Navigation System Using Learning Techniques},
      pages = {121-131},
      booktitle = {From Animals to Animats 13},
      year = {2014},
      volume= {8575},
      editor = {del Pobil, AngelP. and Chinellato, Eris and Martinez-Martin, Ester and Hallam, John and Cervera, Enric and Morales, Antonio},
      language = {English},
      month = {July},
      publisher = {Springer International Publishing},
      series = {Lecture Notes in Computer Science},
      url = {http://dx.doi.org/10.1007/978-3-319-08864-8_12},
      doi = {10.1007/978-3-319-08864-8_12},
      abstract = {The goal-directed navigational ability of animals is an essential prerequisite for them to survive. They can learn to navigate to a distal goal in a complex environment. During this long-distance navigation, they exploit environmental features, like landmarks, to guide them towards their goal. Inspired by this, we develop an adaptive landmark-based navigation system based on sequential reinforcement learning. In addition, correlation-based learning is also integrated into the system to improve learning performance. The proposed system has been applied to simulated simple wheeled and more complex hexapod robots. As a result, it allows the robots to successfully learn to navigate to distal goals in complex environments.}}
    Abstract: The goal-directed navigational ability of animals is an essential prerequisite for them to survive. They can learn to navigate to a distal goal in a complex environment. During this long-distance navigation, they exploit environmental features, like landmarks, to guide them towards their goal. Inspired by this, we develop an adaptive landmark-based navigation system based on sequential reinforcement learning. In addition, correlation-based learning is also integrated into the system to improve learning performance. The proposed system has been applied to simulated simple wheeled and more complex hexapod robots. As a result, it allows the robots to successfully learn to navigate to distal goals in complex environments.
    Review:
    Ren, G. and Chen, W. and Dasgupta, S. and Kolodziejski, C. and Wörgötter, F. and Manoonpong, P. (2014).
    Multiple chaotic central pattern generators with learning for legged locomotion and malfunction compensation. Information Sciences, 666 - 682, 294. DOI: 10.1016/j.ins.2014.05.001.
    BibTeX:
    @article{renchendasgupta2014,
      author = {Ren, G. and Chen, W. and Dasgupta, S. and Kolodziejski, C. and Wörgötter, F. and Manoonpong, P.},
      title = {Multiple chaotic central pattern generators with learning for legged locomotion and malfunction compensation},
      pages = {666 - 682},
      journal = {Information Sciences},
      year = {2014},
      volume= {294},
      month = {05},
      publisher = {Elseiver},
      url = {http://www.sciencedirect.com/science/article/pii/S0020025514005192},
      doi = {10.1016/j.ins.2014.05.001},
      abstract = {An originally chaotic system can be controlled into various periodic dynamics. When it is implemented into a legged robots locomotion control as a central pattern generator CPG, sophisticated gait patterns arise so that the robot can perform various walking behaviors. However, such a single chaotic CPG controller has difficulties dealing with leg malfunction. Specifically, in the scenarios presented here, its movement permanently deviates from the desired trajectory. To address this problem, we extend the single chaotic CPG to multiple CPGs with learning. The learning mechanism is based on a simulated annealing algorithm. In a normal situation, the CPGs synchronize and their dynamics are identical. With leg malfunction or disability, the CPGs lose synchronization leading to independent dynamics. In this case, the learning mechanism is applied to automatically adjust the remaining legs oscillation frequencies so that the robot adapts its locomotion to deal with the malfunction. As a consequence, the trajectory produced by the multiple chaotic CPGs resembles the original trajectory far better than the one produced by only a single CPG. The performance of the system is evaluated first in a physical simulation of a quadruped as well as a hexapod robot and finally in a real six-legged walking machine called AMOSII. The experimental results presented here reveal that using multiple CPGs with learning is an effective approach for adaptive locomotion generation where, for instance, different body parts have to perform independent movements for malfunction compensation}}
    Abstract: An originally chaotic system can be controlled into various periodic dynamics. When it is implemented into a legged robots locomotion control as a central pattern generator CPG, sophisticated gait patterns arise so that the robot can perform various walking behaviors. However, such a single chaotic CPG controller has difficulties dealing with leg malfunction. Specifically, in the scenarios presented here, its movement permanently deviates from the desired trajectory. To address this problem, we extend the single chaotic CPG to multiple CPGs with learning. The learning mechanism is based on a simulated annealing algorithm. In a normal situation, the CPGs synchronize and their dynamics are identical. With leg malfunction or disability, the CPGs lose synchronization leading to independent dynamics. In this case, the learning mechanism is applied to automatically adjust the remaining legs oscillation frequencies so that the robot adapts its locomotion to deal with the malfunction. As a consequence, the trajectory produced by the multiple chaotic CPGs resembles the original trajectory far better than the one produced by only a single CPG. The performance of the system is evaluated first in a physical simulation of a quadruped as well as a hexapod robot and finally in a real six-legged walking machine called AMOSII. The experimental results presented here reveal that using multiple CPGs with learning is an effective approach for adaptive locomotion generation where, for instance, different body parts have to perform independent movements for malfunction compensation
    Review:
    Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2013).
    Active Memory in Input Driven Recurrent Neural Networks. Bernstein Conference 2013. DOI: 10.12751/nncn.bc2013.0151.
    BibTeX:
    @inproceedings{dasguptawoergoettermanoonpong2013a,
      author = {Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {Active Memory in Input Driven Recurrent Neural Networks},
      booktitle = {Bernstein Conference 2013},
      year = {2013},
      doi = {10.12751/nncn.bc2013.0151},
      abstract = {Understanding the exact mechanism of learning and memory emerging from complex dynamical systems like neural networks serves as a challenging field of research. Traditionally the neural mechanisms underlying memory and cognition in these systems are described by steady-state or stable fixed point attractor dynamics. However an alternative and refined understanding of the neuronal dynamics can be achieved through the idea of transient dynamics 1 (reservoir computing paradigm) i.e., computation through input specific trajectories in neural space without stable equilibrium. Mathematical analysis of the underlying memory through such transient dynamics is difficult. As such information theory provides tools to quantify the dynamics of memory in such networks. One such popular measure of memory capacity in reservoir networks is the linear memory capacity 2. It provides an indication of how well the network can reconstruct delayed versions of the input signal. However it assumes a linear retrieval of input signal and deteriorates with neuron non-linearity. Alternatively, active information storage 3 provides a measure of local neuron memory by quantifying the degree of influence of past activity on the next time step activity of a neuron independent of neuronal non-linearity. In this work we further extend this quantity by calculating the mutual information between a neuron past activity and its immediate future activity while conditioning out delayed versions of the input signal. Summing over different delays of input signal it provides a suitable measure of total input driven active memory in the network. Intuitively active memory calculates the actual memory in use i.e. influence of input history on local neuron memory. We compare memory capacity and active memory (AM) with different network parameters for networks driven with statistically different inputs and justify AM as an appropriate means to quantify the dynamics of memory in input driven neural networks.}}
    Abstract: Understanding the exact mechanism of learning and memory emerging from complex dynamical systems like neural networks serves as a challenging field of research. Traditionally the neural mechanisms underlying memory and cognition in these systems are described by steady-state or stable fixed point attractor dynamics. However an alternative and refined understanding of the neuronal dynamics can be achieved through the idea of transient dynamics 1 (reservoir computing paradigm) i.e., computation through input specific trajectories in neural space without stable equilibrium. Mathematical analysis of the underlying memory through such transient dynamics is difficult. As such information theory provides tools to quantify the dynamics of memory in such networks. One such popular measure of memory capacity in reservoir networks is the linear memory capacity 2. It provides an indication of how well the network can reconstruct delayed versions of the input signal. However it assumes a linear retrieval of input signal and deteriorates with neuron non-linearity. Alternatively, active information storage 3 provides a measure of local neuron memory by quantifying the degree of influence of past activity on the next time step activity of a neuron independent of neuronal non-linearity. In this work we further extend this quantity by calculating the mutual information between a neuron past activity and its immediate future activity while conditioning out delayed versions of the input signal. Summing over different delays of input signal it provides a suitable measure of total input driven active memory in the network. Intuitively active memory calculates the actual memory in use i.e. influence of input history on local neuron memory. We compare memory capacity and active memory (AM) with different network parameters for networks driven with statistically different inputs and justify AM as an appropriate means to quantify the dynamics of memory in input driven neural networks.
    Review:
    Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2014).
    Neuromodulatory Adaptive Combination of Correlation-based Learning in Cerebellum and Reward-based Learning in Basal Ganglia for Goal-directed Behavior Control. Frontiers in Neural Circuits, 1 -- 21, 8, 00126. DOI: 10.3389/fncir.2014.00126.
    BibTeX:
    @bibtexentrytype{dasguptawoergoettermanoonpong2014,
      author = {Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {Neuromodulatory Adaptive Combination of Correlation-based Learning in Cerebellum and Reward-based Learning in Basal Ganglia for Goal-directed Behavior Control},
      pages = {1 -- 21},
      journal = {Frontiers in Neural Circuits},
      year = {2014},
      volume= {8},
      number = {00126},
      url = {http://journal.frontiersin.org/Journal/10.3389/fncir.2014.00126/abstract},
      doi = {10.3389/fncir.2014.00126},
      abstract = {Goal-directed decision making in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation-based learning) and operant conditioning (reward-based learning). A number of computational and experimental studies have well established the role of the basal ganglia in reward-based learning, where as the cerebellum plays an important role in developing specific conditioned responses. Although viewed as distinct learning systems, recent animal experiments point towards their complementary role in behavioral learning, and also show the existence of substantial two-way communication between these two brain structures. Based on this notion of co-operative learning, in this paper we hypothesize that the basal ganglia and cerebellar learning systems work in parallel and interact with each other. We envision that such an interaction is influenced by reward modulated heterosynaptic plasticity (RMHP) rule at the thalamus, guiding the overall goal directed behavior. Using a recurrent neural network actor-critic model of the basal ganglia and a feed-forward correlation-based learning model of the cerebellum, we demonstrate that the RMHP rule can effectively balance the outcomes of the two learning systems. This is tested using simulated environments of increasing complexity with a four-wheeled robot in a foraging task in both static and dynamic configurations. Although modeled with a simplified level of biological abstraction, we clearly demonstrate that such a RMHP induced combinatorial learning mechanism, leads to stabler and faster learning of goal-directed behaviors, in comparison to the individual systems. Thus in this paper we provide a computational model for adaptive combination of the basal ganglia and cerebellum learning systems by way of neuromodulated plasticity for goal-directed decision making in biological and bio-mimetic organisms.}}
    Abstract: Goal-directed decision making in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation-based learning) and operant conditioning (reward-based learning). A number of computational and experimental studies have well established the role of the basal ganglia in reward-based learning, where as the cerebellum plays an important role in developing specific conditioned responses. Although viewed as distinct learning systems, recent animal experiments point towards their complementary role in behavioral learning, and also show the existence of substantial two-way communication between these two brain structures. Based on this notion of co-operative learning, in this paper we hypothesize that the basal ganglia and cerebellar learning systems work in parallel and interact with each other. We envision that such an interaction is influenced by reward modulated heterosynaptic plasticity (RMHP) rule at the thalamus, guiding the overall goal directed behavior. Using a recurrent neural network actor-critic model of the basal ganglia and a feed-forward correlation-based learning model of the cerebellum, we demonstrate that the RMHP rule can effectively balance the outcomes of the two learning systems. This is tested using simulated environments of increasing complexity with a four-wheeled robot in a foraging task in both static and dynamic configurations. Although modeled with a simplified level of biological abstraction, we clearly demonstrate that such a RMHP induced combinatorial learning mechanism, leads to stabler and faster learning of goal-directed behaviors, in comparison to the individual systems. Thus in this paper we provide a computational model for adaptive combination of the basal ganglia and cerebellum learning systems by way of neuromodulated plasticity for goal-directed decision making in biological and bio-mimetic organisms.
    Review:
    Dasgupta, S. (2015).
    Temporal information processing and memory guided behaviors with recurrent neural networks. .
    BibTeX:
    @phdthesis{dasgupta2015,
      author = {Dasgupta, S.},
      title = {Temporal information processing and memory guided behaviors with recurrent neural networks},
      year = {2015},
      month = {1},
      url = {https://ediss.uni-goettingen.de/handle/11858/00-1735-0000-0022-5DD2-E?locale-attributeen},
      abstract = {The ability to quantify temporal information on the scale of hundreds of milliseconds is critical towards the processing of complex sensory and motor patterns. However, the nature of neural mechanisms for temporal information processing (at this scale) in the brain still remains largely unknown. Furthermore, given that biological organisms are situated in a dynamic environment, the processing of time-varying environmental stimuli is intricately related to the generation of cognitive behaviors, and as such, an important element of learning and memory. In order to model such temporal processing recurrent neural networks emerge as natural candidates due to their inherent dynamics and fading memory of advent stimuli. As such, this thesis investigates recurrent neural network (RNN) models driven by external stimuli as the basis of time perception and temporal processing in the brain. Such processing lies in the short timescale that is responsible for the generation of short-term memory-guided behaviors like complex motor pattern processing and generation, motor prediction, time-delayed responses, and goal-directed decision making. We present a novel self-adaptive RNN model and verify its ability to generate such complex temporally dependent behaviors, juxtaposing it critically with current state of the art non-adaptive or static RNN models. Taking into consideration the brains ability to undergo changes at structural and functional levels across a wide range of time spans, in this thesis, we make the primary hypothesis, that a combination of neuronal plasticity and homeostatic mechanisms in conjunction with the innate recurrent loops in the underlying neural circuitry gives rise to such temporally-guided actions. Furthermore, unlike most previous studies of spatio-temporal processing in the brain, here we follow a closed-loop approach. Such that, there is a tight coupling between the neural computations and the resultant behaviors, demonstrated on artificial robotic agents as the embodied self of a biological organism. In the first part of the thesis, using a RNN model of rate-coded neurons starting with random initialization of synaptic connections, we propose a learning rule based on local active information storage (LAIS). This is measured at each spatiotemporal location of the network, and used to adapt the individual neuronal decay rates or time constants with respect to the incoming stimuli. This allows an adaptive timescale of the network according to changes in timescales of inputs. We combine this, with a mathematically derived, generalized mutual information driven intrinsic plasticity mechanism that can tune the non-linearity of network neurons. This enables the network to maintain homeostasis as well as, maximize the flow of information from input stimuli to neuronal outputs. These unsupervised local adaptations are then combined with supervised synaptic plasticity in order to tune the otherwise fixed synaptic connections, in a task dependent manner. The resultant plastic network, significantly outperforms previous static models for complex temporal processing tasks in non-linear computing power, temporal memory capacity, noise robustness as well as tuning towards near-critical dynamics. These are displayed using a number of benchmark tests, delayed memory guided responses with a robotic agent in real environment and complex motor pattern generation tasks. Furthermore, we also demonstrate the ability of our adaptive network to generate clock like behaviors underlying time perception in the brain. The model output matches the linear relationship of variance and squared time interval as observed from experimental studies. In the second part of the thesis, we first demonstrate the application of our model on behaviorally relevant motor prediction tasks with a walking robot, implementing distributed internal forward models using our adaptive network. Following this, we extend the previous supervised learning scheme, by implementing reward-based learning following the temporal-difference paradigm, in order to adapt the synaptic connections in our network. The neuronal correlates of this formulation is discussed from the point of view of the cortico-striatal circuitry, and a new combined learning rule is presented. This leads to novel results demonstrating how the striatal circuitry works in combination with the cerebellar circuitry in the brain, that lead to robust goal-directed behaviors. Thus, we demonstrate the application of our adaptive network model on the entire spectrum of temporal information processing, in the timescale of few hundred milliseconds (complex motor processing) to minutes (delayed memory and decision making). Overall, the results obtained in this thesis affirms our primary hypothesis that plasticity and adaptation in recurrent networks allow complex temporal information processing, which otherwise cannot be obtained with purely static networks. Furthermore, homeostatic plasticity and neuronal timescale adaptations could be potential mechanisms by which the brain performs such processing with remarkable ease.}}
    Abstract: The ability to quantify temporal information on the scale of hundreds of milliseconds is critical towards the processing of complex sensory and motor patterns. However, the nature of neural mechanisms for temporal information processing (at this scale) in the brain still remains largely unknown. Furthermore, given that biological organisms are situated in a dynamic environment, the processing of time-varying environmental stimuli is intricately related to the generation of cognitive behaviors, and as such, an important element of learning and memory. In order to model such temporal processing recurrent neural networks emerge as natural candidates due to their inherent dynamics and fading memory of advent stimuli. As such, this thesis investigates recurrent neural network (RNN) models driven by external stimuli as the basis of time perception and temporal processing in the brain. Such processing lies in the short timescale that is responsible for the generation of short-term memory-guided behaviors like complex motor pattern processing and generation, motor prediction, time-delayed responses, and goal-directed decision making. We present a novel self-adaptive RNN model and verify its ability to generate such complex temporally dependent behaviors, juxtaposing it critically with current state of the art non-adaptive or static RNN models. Taking into consideration the brains ability to undergo changes at structural and functional levels across a wide range of time spans, in this thesis, we make the primary hypothesis, that a combination of neuronal plasticity and homeostatic mechanisms in conjunction with the innate recurrent loops in the underlying neural circuitry gives rise to such temporally-guided actions. Furthermore, unlike most previous studies of spatio-temporal processing in the brain, here we follow a closed-loop approach. Such that, there is a tight coupling between the neural computations and the resultant behaviors, demonstrated on artificial robotic agents as the embodied self of a biological organism. In the first part of the thesis, using a RNN model of rate-coded neurons starting with random initialization of synaptic connections, we propose a learning rule based on local active information storage (LAIS). This is measured at each spatiotemporal location of the network, and used to adapt the individual neuronal decay rates or time constants with respect to the incoming stimuli. This allows an adaptive timescale of the network according to changes in timescales of inputs. We combine this, with a mathematically derived, generalized mutual information driven intrinsic plasticity mechanism that can tune the non-linearity of network neurons. This enables the network to maintain homeostasis as well as, maximize the flow of information from input stimuli to neuronal outputs. These unsupervised local adaptations are then combined with supervised synaptic plasticity in order to tune the otherwise fixed synaptic connections, in a task dependent manner. The resultant plastic network, significantly outperforms previous static models for complex temporal processing tasks in non-linear computing power, temporal memory capacity, noise robustness as well as tuning towards near-critical dynamics. These are displayed using a number of benchmark tests, delayed memory guided responses with a robotic agent in real environment and complex motor pattern generation tasks. Furthermore, we also demonstrate the ability of our adaptive network to generate clock like behaviors underlying time perception in the brain. The model output matches the linear relationship of variance and squared time interval as observed from experimental studies. In the second part of the thesis, we first demonstrate the application of our model on behaviorally relevant motor prediction tasks with a walking robot, implementing distributed internal forward models using our adaptive network. Following this, we extend the previous supervised learning scheme, by implementing reward-based learning following the temporal-difference paradigm, in order to adapt the synaptic connections in our network. The neuronal correlates of this formulation is discussed from the point of view of the cortico-striatal circuitry, and a new combined learning rule is presented. This leads to novel results demonstrating how the striatal circuitry works in combination with the cerebellar circuitry in the brain, that lead to robust goal-directed behaviors. Thus, we demonstrate the application of our adaptive network model on the entire spectrum of temporal information processing, in the timescale of few hundred milliseconds (complex motor processing) to minutes (delayed memory and decision making). Overall, the results obtained in this thesis affirms our primary hypothesis that plasticity and adaptation in recurrent networks allow complex temporal information processing, which otherwise cannot be obtained with purely static networks. Furthermore, homeostatic plasticity and neuronal timescale adaptations could be potential mechanisms by which the brain performs such processing with remarkable ease.
    Review:
    Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2014).
    Goal-directed Learning with Reward Modulated Interaction between Striatal and Cerebellar Systems. Bernstein Conference 2014, 1 -- 1. DOI: 10.12751/nncn.bc2014.0177.
    BibTeX:
    @inproceedings{dasguptawoergoettermanoonpong2014a,
      author = {Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {Goal-directed Learning with Reward Modulated Interaction between Striatal and Cerebellar Systems},
      pages = {1 -- 1},
      booktitle = {Bernstein Conference 2014},
      year = {2014},
      month = {Sept},
      doi = {10.12751/nncn.bc2014.0177},
      abstract = {Goal-directed decision making in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation based learning) and operand conditioning (reward-based learning). A number of computational and experimental studies have well established the role of the basal ganglia (striatal system) towards reward-based learning, where as the cerebellum evidently plays an important role in developing specific conditioned responses. Although, they are viewed as distinct learning systems 1, recent animal experiments point towards their complementary role in behavioral learning, and also show the existence of substantial two-way communication between the two structures 2. Based on this notion of co-operative learning, in this work we hypothesize that the basal ganglia and cerebellar learning systems work in parallel and compete with each other (Figure 1). We envision such an interaction being driven by a simple reward modulated heterosynaptic plasticity (RMHP) rule 3, in order to guide the over all goal-directed behavior. Using a recurrent neural network actor-critic model of the basal ganglia and feed-forward correlation learning model of the cerebellum (input correlation learning-ICO) 4, we demonstrate that the RMHP rule can effectively combine the outcomes of the two learning systems. This is tested using simulated environments of increasing complexity with a four-wheeled animat in a dynamic foraging task. Although, they are modeled within a highly simplified level of biological abstraction, we clearly demonstrate that such a combined learning mechanism, leads to much stabler and faster learning of goal-directed behaviors in comparison to the individual systems.}}
    Abstract: Goal-directed decision making in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation based learning) and operand conditioning (reward-based learning). A number of computational and experimental studies have well established the role of the basal ganglia (striatal system) towards reward-based learning, where as the cerebellum evidently plays an important role in developing specific conditioned responses. Although, they are viewed as distinct learning systems 1, recent animal experiments point towards their complementary role in behavioral learning, and also show the existence of substantial two-way communication between the two structures 2. Based on this notion of co-operative learning, in this work we hypothesize that the basal ganglia and cerebellar learning systems work in parallel and compete with each other (Figure 1). We envision such an interaction being driven by a simple reward modulated heterosynaptic plasticity (RMHP) rule 3, in order to guide the over all goal-directed behavior. Using a recurrent neural network actor-critic model of the basal ganglia and feed-forward correlation learning model of the cerebellum (input correlation learning-ICO) 4, we demonstrate that the RMHP rule can effectively combine the outcomes of the two learning systems. This is tested using simulated environments of increasing complexity with a four-wheeled animat in a dynamic foraging task. Although, they are modeled within a highly simplified level of biological abstraction, we clearly demonstrate that such a combined learning mechanism, leads to much stabler and faster learning of goal-directed behaviors in comparison to the individual systems.
    Review:
    Goldschmidt, D. and Dasgupta, S. and Wörgötter, F. and Manoonpong, P. (2015).
    A Neural Path Integration Mechanism for Adaptive Vector Navigation in Autonomous Agents. International Joint Conference on Neural Networks (IJCNN), neural path integration mechanism for adaptive vector navigation in autonomous agents, 1-8. DOI: 10.1109/IJCNN.2015.7280400.
    BibTeX:
    @inproceedings{goldschmidtdasguptawoergoetter2015,
      author = {Goldschmidt, D. and Dasgupta, S. and Wörgötter, F. and Manoonpong, P.},
      title = {A Neural Path Integration Mechanism for Adaptive Vector Navigation in Autonomous Agents},
      pages = {1-8},
      booktitle = {International Joint Conference on Neural Networks (IJCNN), neural path integration mechanism for adaptive vector navigation in autonomous agents},
      year = {2015},
      month = {July},
      doi = {10.1109/IJCNN.2015.7280400},
      abstract = {Animals show remarkable capabilities in navigating their habitat in a fully autonomous and energy-efficient way. In many species, these capabilities rely on a process called path integration, which enables them to estimate their current location and to find their way back home after long-distance journeys. Path integration is achieved by integrating compass and odometric cues. Here we introduce a neural path integration mechanism that interacts with a neural locomotion control to simulate homing behavior and path integration-related behaviors observed in animals. The mechanism is applied to a simulated six-legged artificial agent. Input signals from an allothetic compass and odometry are sustained through leaky neural integrator circuits, which are then used to compute the home vector by local excitation-global inhibition interactions. The home vector is computed and represented in circular arrays of neurons, where compass directions are population-coded and linear displacements are rate-coded. The mechanism allows for robust homing behavior in the presence of external sensory noise. The emergent behavior of the controlled agent does not only show a robust solution for the problem of autonomous agent navigation, but it also reproduces various aspects of animal navigation. Finally, we discuss how the proposed path integration mechanism may be used as a scaffold for spatial learning in terms of vector navigation.}}
    Abstract: Animals show remarkable capabilities in navigating their habitat in a fully autonomous and energy-efficient way. In many species, these capabilities rely on a process called path integration, which enables them to estimate their current location and to find their way back home after long-distance journeys. Path integration is achieved by integrating compass and odometric cues. Here we introduce a neural path integration mechanism that interacts with a neural locomotion control to simulate homing behavior and path integration-related behaviors observed in animals. The mechanism is applied to a simulated six-legged artificial agent. Input signals from an allothetic compass and odometry are sustained through leaky neural integrator circuits, which are then used to compute the home vector by local excitation-global inhibition interactions. The home vector is computed and represented in circular arrays of neurons, where compass directions are population-coded and linear displacements are rate-coded. The mechanism allows for robust homing behavior in the presence of external sensory noise. The emergent behavior of the controlled agent does not only show a robust solution for the problem of autonomous agent navigation, but it also reproduces various aspects of animal navigation. Finally, we discuss how the proposed path integration mechanism may be used as a scaffold for spatial learning in terms of vector navigation.
    Review:
    Tetzlaff, C. and Dasgupta, S. and Kulvicius, T. and Wörgötter, F. (2015).
    The Use of Hebbian Cell Assemblies for Nonlinear Computation. Scientific Reports, 5. DOI: 10.1038/srep12866.
    BibTeX:
    @article{tetzlaffdasguptakulvicius2015,
      author = {Tetzlaff, C. and Dasgupta, S. and Kulvicius, T. and Wörgötter, F.},
      title = {The Use of Hebbian Cell Assemblies for Nonlinear Computation},
      journal = {Scientific Reports},
      year = {2015},
      volume= {5},
      publisher = {Nature Publishing Group},
      url = {http://www.nature.com/articles/srep12866},
      doi = {10.1038/srep12866},
      abstract = {When learning a complex task our nervous system self-organizes large groups of neurons into coherent dynamic activity patterns. During this, a network with multiple, simultaneously active, and computationally powerful cell assemblies is created. How such ordered structures are formed while preserving a rich diversity of neural dynamics needed for computation is still unknown. Here we show that the combination of synaptic plasticity with the slower process of synaptic scaling achieves (i) the formation of cell assemblies and (ii) enhances the diversity of neural dynamics facilitating the learning of complex calculations. Due to synaptic scaling the dynamics of different cell assemblies do not interfere with each other. As a consequence, this type of self-organization allows executing a difficult, six degrees of freedom, manipulation task with a robot where assemblies need to learn computing complex non-linear transforms and - for execution - must cooperate with each other without interference. This mechanism, thus, permits the self-organization of computationally powerful sub-structures in dynamic networks for behavior control.}}
    Abstract: When learning a complex task our nervous system self-organizes large groups of neurons into coherent dynamic activity patterns. During this, a network with multiple, simultaneously active, and computationally powerful cell assemblies is created. How such ordered structures are formed while preserving a rich diversity of neural dynamics needed for computation is still unknown. Here we show that the combination of synaptic plasticity with the slower process of synaptic scaling achieves (i) the formation of cell assemblies and (ii) enhances the diversity of neural dynamics facilitating the learning of complex calculations. Due to synaptic scaling the dynamics of different cell assemblies do not interfere with each other. As a consequence, this type of self-organization allows executing a difficult, six degrees of freedom, manipulation task with a robot where assemblies need to learn computing complex non-linear transforms and - for execution - must cooperate with each other without interference. This mechanism, thus, permits the self-organization of computationally powerful sub-structures in dynamic networks for behavior control.
    Review:
    Dasgupta, S. and Goldschmidt, D. and Wörgötter, F. and Manoonpong, P. (2015).
    Distributed Recurrent Neural Forward Models with Synaptic Adaptation for Complex Behaviors of Walking Robots. arXiv preprint arXiv:1506.03599.
    BibTeX:
    @article{dasguptagoldschmidtwoergoetter2015,
      author = {Dasgupta, S. and Goldschmidt, D. and Wörgötter, F. and Manoonpong, P.},
      title = {Distributed Recurrent Neural Forward Models with Synaptic Adaptation for Complex Behaviors of Walking Robots},
      journal = {arXiv preprint arXiv:1506.03599},
      year = {2015},
      url = {http://arxiv.org/abs/1506.03599},
      abstract = {Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biome- chanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of in- ternal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively com- bines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of 1) central pattern generator based control for generating basic rhythmic patterns and coordinated movements, 2) distributed (at each leg) recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and 3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex loco- motive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps as well as climbing over high obstacles.}}
    Abstract: Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biome- chanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of in- ternal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively com- bines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of 1) central pattern generator based control for generating basic rhythmic patterns and coordinated movements, 2) distributed (at each leg) recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and 3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex loco- motive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps as well as climbing over high obstacles.
    Review:

    © 2011 - 2017 Dept. of Computational Neuroscience • comments to: sreich _at_ gwdg.de • Impressum / Site Info