The Importance of Space and Time for Signal Processing in Neuromorphic Agents: The Challenge of Developing Low-Power, Autonomous Agents That Interact With the Environment

Artificial neural networks (ANNs) and computational neuroscience models have made tremendous progress, enabling us to achieve impressive results in artificial intelligence applications, such as image recognition, natural language processing, and autonomous driving. Despite this, biological neural systems consume orders of magnitude less energy than today's ANNs and are much more flexible and robust. This adaptivity and efficiency gap is partially explained by the computing substrate of biological neural processing systems that is fundamentally different from the way today?s computers are built. Biological systems use in-memory computing elements operating in a massively parallel way rather than time-multiplexed computing units that are reused in a sequential fashion. Moreover, the activity of biological neurons follows continuous-time dynamics in real, physical time instead of operating on discrete temporal cycles abstracted away from real time.

[1]  Wei Ji Ma,et al.  Bayesian inference with probabilistic population codes , 2006, Nature Neuroscience.

[2]  Yulia Sandamirskaya,et al.  Dynamic neural fields as a step toward cognitive neuromorphic architectures , 2014, Front. Neurosci..

[3]  Thomas Rost,et al.  A neuromorphic approach to auditory pattern recognition in cricket phonotaxis , 2013, 2013 European Conference on Circuit Theory and Design (ECCTD).

[4]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[5]  Tobi Delbrück,et al.  ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation , 2017, ArXiv.

[6]  Yulia Sandamirskaya,et al.  A Neuromorphic Approach to Path Integration: A Head-Direction Spiking Neural Network with Vision-driven Reset , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[7]  Mostafa Rahimi Azghadi,et al.  Spike-Based Synaptic Plasticity in Silicon: Design, Implementation, Application, and Challenges , 2014, Proceedings of the IEEE.

[8]  Christofer Toumazou,et al.  Analogue IC design : the current-mode approach , 1993 .

[9]  Subhrajit Roy,et al.  A current-mode spiking neural classifier with lumped dendritic nonlinearity , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[10]  Stephan K. U. Zibner,et al.  Using Dynamic Field Theory to extend the embodiment stance toward higher cognition , 2013 .

[11]  Giacomo Indiveri,et al.  A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: From mitigation to exploitation , 2018, Faraday discussions.

[12]  Arindam Basu,et al.  A Learning-Enabled Neuron Array IC Based Upon Transistor Channel Models of Biological Phenomena , 2013, IEEE Transactions on Biomedical Circuits and Systems.

[13]  Johannes Schemmel,et al.  Modeling Synaptic Plasticity within Networks of Highly Accelerated I&F Neurons , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[14]  Giacomo Indiveri,et al.  Systematic Construction of Finite State Automata Using VLSI Spiking Neurons , 2012, Living Machines.

[15]  Giacomo Indiveri,et al.  A Scalable Multicore Architecture With Heterogeneous Memory Structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs) , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[16]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

[17]  Steve B. Furber,et al.  Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype , 2018, Front. Neurosci..

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  David Bol,et al.  A 0.086-mm2 12.7-pJ/SOP 64k-Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28-nm CMOS , 2019, IEEE Trans. Biomed. Circuits Syst..

[20]  Antoine Dupret,et al.  Event-Based, Timescale Invariant Unsupervised Online Deep Learning With STDP , 2018, Front. Comput. Neurosci..

[21]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[22]  Jeffrey S. Johnson,et al.  Moving to higher ground: The dynamic field theory and the dynamics of visual cognition. , 2008, New ideas in psychology.

[23]  W. Senn,et al.  Learning by the Dendritic Prediction of Somatic Spiking , 2014, Neuron.

[24]  R. Douglas,et al.  Neuronal circuits of the neocortex. , 2004, Annual review of neuroscience.

[25]  Nicolas Brunel,et al.  NETWORK MODELS OF MEMORY , 2004 .

[26]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

[27]  Chris Eliasmith,et al.  Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems , 2004, IEEE Transactions on Neural Networks.

[28]  Luca Benini,et al.  A ultra-low-energy convolution engine for fast brain-inspired vision in multicore clusters , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[29]  Giacomo Indiveri,et al.  A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses , 2015, Front. Neurosci..

[30]  Florentin Wörgötter,et al.  Dynamic Neural Fields with Intrinsic Plasticity , 2017, Front. Comput. Neurosci..

[31]  Somnath Paul,et al.  Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines , 2016, Front. Neurosci..

[32]  Chiara Bartolozzi,et al.  An Ultralow Leakage Synaptic Scaling Homeostatic Plasticity Circuit With Configurable Time Scales up to 100 ks , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[33]  Stephan K. U. Zibner,et al.  Developing Dynamic Field Theory Architectures for Embodied Cognitive Systems with cedar , 2016, Front. Neurorobot..

[34]  Patrick Camilleri,et al.  A VLSI network of spiking neurons with plastic fully configurable “stop-learning” synapses , 2008, 2008 15th IEEE International Conference on Electronics, Circuits and Systems.

[35]  Chiara Bartolozzi,et al.  Synaptic Dynamics in Analog VLSI , 2007, Neural Computation.

[36]  Giacomo Indiveri,et al.  Synthesizing cognition in neuromorphic electronic systems , 2013, Proceedings of the National Academy of Sciences.

[37]  Yulia Sandamirskaya,et al.  Learning the Condition of Satisfaction of an Elementary Behavior in Dynamic Field Theory , 2015, Paladyn J. Behav. Robotics.

[38]  Giacomo Indiveri,et al.  Real-Time Classification of Complex Patterns Using Spike-Based Learning in Neuromorphic VLSI , 2009, IEEE Transactions on Biomedical Circuits and Systems.

[39]  Gert Cauwenberghs,et al.  Neuromorphic Silicon Neuron Circuits , 2011, Front. Neurosci.

[40]  Giacomo Indiveri,et al.  Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic Processing System , 2017, Front. Neurorobot..

[41]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[42]  Yulia Sandamirskaya,et al.  Learning to Look and Looking to Remember: A Neural-Dynamic Embodied Model for Generation of Saccadic Gaze Shifts and Memory Formation , 2015 .

[43]  Dean V. Buonomano,et al.  The Neural Basis of Timing: Distributed Mechanisms for Diverse Functions , 2018, Neuron.

[44]  Jongkil Park,et al.  A 65k-neuron 73-Mevents/s 22-pJ/event asynchronous micro-pipelined integrate-and-fire array transceiver , 2014, 2014 IEEE Biomedical Circuits and Systems Conference (BioCAS) Proceedings.

[45]  Yulia Sandamirskaya,et al.  Pose Estimation and Map Formation with Spiking Neural Networks: towards Neuromorphic SLAM , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[46]  Jean-Jacques E. Slotine,et al.  Collective Stability of Networks of Winner-Take-All Circuits , 2011, Neural Computation.

[47]  Giacomo Indiveri,et al.  A neuromorphic controller for a robotic vehicle equipped with a dynamic vision sensor , 2017, Robotics: Science and Systems.

[48]  S. Amari.  Dynamics of pattern formation in lateral-inhibition type neural fields , 1977, Biological Cybernetics.

[49]  Gregor Schöner,et al.  Dynamic Thinking : A Primer on Dynamic Field Theory , 2015 .

[50]  Wolfgang Maass,et al.  On the Computational Power of Winner-Take-All , 2000, Neural Computation.

[51]  Giacomo Indiveri,et al.  Organizing Sequential Memory in a Neuromorphic Device Using Dynamic Neural Fields , 2018, Front. Neurosci..

[52]  Gregor Schöner,et al.  An embodied account of serial order: How instabilities drive sequence generation , 2010, Neural Networks.

[53]  Rodrigo Alvarez-Icaza,et al.  Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations , 2014, Proceedings of the IEEE.

[54]  Giacomo Indiveri,et al.  On-chip unsupervised learning in winner-take-all networks of spiking neurons , 2017, 2017 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[55]  W. Newsome,et al.  Context-dependent computation by recurrent dynamics in prefrontal cortex , 2013, Nature.

[56]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[57]  Giacomo Indiveri,et al.  Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[58]  R. Douglas,et al.  Recurrent neuronal circuits in the neocortex , 2007, Current Biology.

[59]  J. Cowan,et al.  A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue , 1973, Kybernetik.

[60]  J. K. Fidler,et al.  Analogue IC Design: the Current-Mode Approach , 1991 .

[61]  Catalin V. Buhusi,et al.  What makes us tick? Functional and neural mechanisms of interval timing , 2005, Nature Reviews Neuroscience.

[62]  Yulia Sandamirskaya,et al.  Learning Temporal Intervals in Neural Dynamics , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[63]  R. Douglas,et al.  Event-Based Neuromorphic Systems , 2015 .

[64]  David Bol,et al.  A 0.086-mm$^2$ 12.7-pJ/SOP 64k-Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28-nm CMOS , 2018, IEEE Transactions on Biomedical Circuits and Systems.

[65]  Yulia Sandamirskaya,et al.  Learning Sensorimotor Transformations with Dynamic Neural Fields , 2013, ICANN.

[66]  Chiara Bartolozzi,et al.  Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems , 2014, Proceedings of the IEEE.

[67]  Vittorio Dante,et al.  A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory , 2003, IEEE Trans. Neural Networks.

[68]  Gregor Schöner,et al.  Parsing of action sequences: A neural dynamics approach , 2015, Paladyn J. Behav. Robotics.

[69]  Steve B. Furber,et al.  The SpiNNaker Project , 2014, Proceedings of the IEEE.

[70]  Alessandro Aimar,et al.  NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[71]  Johannes Schemmel,et al.  A wafer-scale neuromorphic hardware system for large-scale neural modeling , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[72]  Jürgen Schmidhuber,et al.  Autonomous reinforcement of behavioral sequences in neural dynamics , 2012, The 2013 International Joint Conference on Neural Networks (IJCNN).

[73]  Giacomo Indiveri,et al.  Memory and Information Processing in Neuromorphic Systems , 2015, Proceedings of the IEEE.

[74]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.