A reservoir computing model of episodic memory

We present a novel neural episodic memory architecture that utilizes reservoir computing to extract and recall information gleaned over time from a multilayer perceptron that receives sensory input. Reservoir computing models project input data into a high-dimensional dynamical space and also serve as a fading memory that holds on to past inputs thereby enabling the direct association of the current input with the past. The architecture presented utilizes these capabilities via an abstract feedback mechanism and in doing so creates attractor-like states within the reservoir that are associated with each discrete memory and associates these states and therefore memories over time into episodes. In addition, the feedback mechanism provides stabilization to an otherwise chaotic complex dynamical system.

[1]  Alan D Baddeley,et al.  Memory for serial order across domains: An overview of the literature and directions for future research. , 2014, Psychological bulletin.

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

[3]  Maryam Gholami Doborjeh,et al.  Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications , 2016, Neural Networks.

[4]  Sean M. Polyn,et al.  The Cambridge Handbook of Computational Psychology: Computational Models of Episodic Memory , 2008 .

[5]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[6]  M. Hasselmo,et al.  A biologically inspired hierarchical goal directed navigation model , 2014, Journal of Physiology-Paris.

[7]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[8]  Bennet B. Murdock,et al.  Developing TODAM: Three models for serial-order information , 1995, Memory & cognition.

[9]  Benjamin Schrauwen,et al.  Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons , 2010, Neural Computation.

[10]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[11]  Mantas Lukosevicius,et al.  A Practical Guide to Applying Echo State Networks , 2012, Neural Networks: Tricks of the Trade.

[12]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[13]  Yaochu Jin,et al.  Modeling neural plasticity in echo state networks for time series prediction , 2014, 2014 14th UK Workshop on Computational Intelligence (UKCI).

[14]  K. Norman.  How hippocampus and cortex contribute to recognition memory: Revisiting the complementary learning systems model , 2010, Hippocampus.

[15]  Benjamin Schrauwen,et al.  Recurrent Kernel Machines: Computing with Infinite Echo State Networks , 2012, Neural Computation.

[16]  Dean V. Buonomano,et al.  ROBUST TIMING AND MOTOR PATTERNS BY TAMING CHAOS IN RECURRENT NEURAL NETWORKS , 2012, Nature Neuroscience.

[17]  Alex Fradera,et al.  Memory for time: The use of temporal codes versus contextual information. , 2006 .

[18]  R. O’Reilly,et al.  Modeling hippocampal and neocortical contributions to recognition memory: a complementary-learning-systems approach. , 2003, Psychological review.

[19]  Hedda Rahel Schmidtke,et al.  Delayed Synapses: An LSM Model for Studying Aspects of Temporal Context in Memory , 2011, CONTEXT.

[20]  Jacob Benesty,et al.  Recursive Least-Squares Algorithms , 2011 .

[21]  Ron Sun,et al.  The Cambridge Handbook of Computational Psychology , 2008 .

[22]  Sommers,et al.  Chaos in random neural networks. , 1988, Physical review letters.

[23]  Marc W Howard,et al.  A context-based theory of recency and contiguity in free recall. , 2008, Psychological review.

[24]  Uğur M Erdem,et al.  A goal‐directed spatial navigation model using forward trajectory planning based on grid cells , 2012, The European journal of neuroscience.

[25]  Naoyuki Sato,et al.  Simulation of Human Episodic Memory by Using a Computational Model of the Hippocampus , 2010, Adv. Artif. Intell..

[26]  Benjamin Schrauwen,et al.  Reservoir Computing Trends , 2012, KI - Künstliche Intelligenz.

[27]  Stefan Rotter,et al.  Increased robustness and intermittent dynamics in structured Reservoir Networks with feedback , 2011, ESANN.

[28]  I. Neath.  Human Memory: An Introduction to Research, Data, and Theory , 1997 .

[29]  J. Townsend,et al.  The Oxford Handbook of Computational and Mathematical Psychology , 2015 .

[30]  B. Murdock,et al.  Memory for Serial Order , 1989 .

[31]  L. F. Abbott,et al.  Generating Coherent Patterns of Activity from Chaotic Neural Networks , 2009, Neuron.

[32]  Wolfgang Maass,et al.  Information Dynamics and Emergent Computation in Recurrent Circuits of Spiking Neurons , 2003, NIPS.