Advances in SHRUTI—A Neurally Motivated Model of Relational Knowledge Representation and Rapid Inference Using Temporal Synchrony

We are capable of drawing a variety of inferences effortlessly, spontaneously, and with remarkable efficiency—as though these inferences are a reflex response of our cognitive apparatus. This remarkable human ability poses a challenge for cognitive science and computational neuroscience: How can a network of slow neuron-like elements represent a large body of systematic knowledge and perform a wide range of inferences with such speed? The connectionist model SHRUTI attempts to address this challenge by demonstrating how a neurally plausible network can encode a large body of semantic and episodic facts, systematic rules, and knowledge about entities and types, and yet perform a wide range of explanatory and predictive inferences within a few hundred milliseconds. Relational structures (frames, schemas) are represented in SHRUTI by clusters of cells, and inference in SHRUTI corresponds to a transient propagation of rhythmic activity over such cell-clusters wherein dynamic bindings are represented by the synchronous firing of appropriate cells. SHRUTI encodes mappings across relational structures using high-efficacy links that enable the propagation of rhythmic activity, and it encodes items in long-term memory as coincidence and coincidence-error detector circuits that become active in response to the occurrence (or non-occurrence) of appropriate coincidences in the on going flux of rhythmic activity. Finally, “understanding” in SHRUTI corresponds to reverberant and coherent activity along closed loops of neural circuitry. Over the past several years, SHRUTI has undergone several enhancements that have augmented its expressiveness and inferential power. This paper describes some of these extensions that enable SHRUTI to (i) deal with negation and inconsistent beliefs, (ii) encode evidential rules and facts, (iii) perform inferences requiring the dynamic instantiation of entities, and (iv) seek coherent explanations of observations.

[1]  Antonio R. Damasio,et al.  The Brain Binds Entities and Events by Multiregional Activation from Convergence Zones , 1989, Neural Computation.

[2]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[3]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .

[4]  Lokendra Shastri,et al.  An Optimally Efficient Limited Inference System , 1990, AAAI.

[5]  Michael Gasser,et al.  Where Do Relations Come From , 1998 .

[6]  G. W. Strong,et al.  Phase logic is biologically relevant logic , 1993, Behavioral and Brain Sciences.

[7]  Lokendra Shastri,et al.  Rules and Variables in Neural Nets , 1991, Neural Computation.

[8]  W Singer,et al.  Visual feature integration and the temporal correlation hypothesis. , 1995, Annual review of neuroscience.

[9]  Lokendra Shastri,et al.  A Connectionist Encoding of Schemas and Reactive Plans , 1997 .

[10]  Christof Koch,et al.  A model for the neuronal implementation of selective visual attention based on temporal correlation among neurons , 1994, Journal of Computational Neuroscience.

[11]  Terry Regier,et al.  The Human Semantic Potential: Spatial Language and Constrained Connectionism , 1996 .

[12]  E. Vaadia,et al.  Spatiotemporal firing patterns in the frontal cortex of behaving monkeys. , 1993, Journal of neurophysiology.

[13]  F. Crick.  Function of the thalamic reticular complex: the searchlight hypothesis. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[14]  W. Kintsch.  The role of knowledge in discourse comprehension: a construction-integration model. , 1988, Psychological review.

[15]  John A. Barnden,et al.  Encoding techniques for complex information structures in connectionist systems , 1991 .

[16]  James Henderson,et al.  Connectionist syntactic parsing using temporal variable binding , 1994 .

[17]  P. Milner.  A model for visual shape recognition. , 1974, Psychological review.

[18]  Michael G. Dyer,et al.  High-level Inferencing in a Connectionist Network , 1989 .

[19]  G. W. Strong,et al.  A solution to the tag-assignment problem for neural networks , 1989, Behavioral and Brain Sciences.

[20]  Lokendra Shastri,et al.  Structured connectionist models , 1998 .

[21]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[22]  Jerome A. Feldman,et al.  Extending Embodied Lexical Development , 1998 .

[23]  L. Shastri,et al.  From Simple Associations to Systemic Reasoning: A Connectionist Representation of Rules, Variables and Dynamic Bindings , 1990 .

[24]  Lokendra Shastri,et al.  Types and Quantifiers in SHRUTI: A Connectionist Model of Rapid Reasoning and Relational Processing , 1998, Hybrid Neural Systems.

[25]  O Jensen,et al.  Novel lists of 7 +/- 2 known items can be reliably stored in an oscillatory short-term memory network: interaction with long-term memory. , 1996, Learning & memory.

[26]  E. Tulving.  Elements of episodic memory , 1983 .

[27]  Jared Freeman,et al.  Metarecognition in Time-Stressed Decision Making: Recognizing, Critiquing, and Correcting , 1996, Hum. Factors.

[28]  Professor Moshe Abeles,et al.  Local Cortical Circuits , 1982, Studies of Brain Function.

[29]  L. Nadel,et al.  The Hippocampus as a Cognitive Map , 1978 .

[30]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[31]  Leslie G. Valiant,et al.  Circuits of the mind , 1994 .

[32]  R. Eckhorn,et al.  Coherent oscillations: A mechanism of feature linking in the visual cortex? , 1988, Biological Cybernetics.

[33]  E. Bienenstock.  A model of neocortex , 1995 .

[34]  D. R. Mani,et al.  The design and implementation of massively parallel knowledge representation and reasoning systems: a connectionist approach , 1996 .

[35]  R. Ratcliff,et al.  The comprehension processes and memory structures involved in instrumental inference , 1981 .

[36]  W. Singer.  Synchronization of cortical activity and its putative role in information processing and learning. , 1993, Annual review of physiology.

[37]  Venkat Ajjanagadde,et al.  Incorporating background knowledge and structured explananda in abductive reasoning: a framework , 1993, IEEE Trans. Syst. Man Cybern..

[38]  Keith Stenning,et al.  Extension of the temporal synchrony approach to dynamic variable bindingin a connectionist inference system , 1995, Knowl. Based Syst..

[39]  R. Christopher deCharms,et al.  Primary cortical representation of sounds by the coordination of action-potential timing , 1996, Nature.

[40]  G. R. Potts,et al.  Assessing the occurrence of elaborative inferences: Lexical decision versus naming , 1988 .

[41]  Lokendra Shastri,et al.  Temporal synchrony, dynamic bindings, and Shruti: A representational but nonclassical model of reflexive reasoning , 1996, Behavioral and Brain Sciences.

[42]  Jerome A. Feldman,et al.  Neural Representation of Conceptual Knowledge. , 1986 .

[43]  L. Shastri,et al.  A Connectionist Treatment of Negation and Inconsistency , 1996 .

[44]  Lokendra Shastri,et al.  The Relevance of Connectionism to AI: A Representation and Reasoning Perspective , 1989 .

[45]  Alessandro Sperduti,et al.  A general framework for adaptive processing of data structures , 1998, IEEE Trans. Neural Networks.

[46]  Lokendra Shastri,et al.  A Computational Model of Tractable Reasoning - Taking Inspiration from Cognition , 1993, IJCAI.

[47]  Lokendra Shastri,et al.  Exploiting Temporal Binding to Learn Relational Rules within a Connectionist Network , 1997 .

[48]  M. Just,et al.  From the SelectedWorks of Marcel Adam Just 1992 A capacity theory of comprehension : Individual differences in working memory , 2017 .

[49]  Lokendra Shastri,et al.  Soft Computing in SHRUTI - A Neurally Plausible Model of Reflexive Reasoning and Relational Information Processing , 1999, IIA/SOCO.

[50]  D. R. Mani,et al.  Massively parallel knowledge representation and reasoning: Taking a cue from the brain , 1997, Parallel Processing for Artificial Intelligence 3.

[51]  Christoph Goller,et al.  Learning task-dependent distributed representations by backpropagation through structure , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[52]  Walter J. Freeman,et al.  Deconstruction of neural data yields biologically implausible periodic oscillations , 1993, Behavioral and Brain Sciences.

[53]  Edward K. Vogel,et al.  The capacity of visual working memory for features and conjunctions , 1997, Nature.

[54]  Jacques Sougné,et al.  Connectionism and the problem of multiple instantiation , 1998, Trends in Cognitive Sciences.

[55]  Vipin Kumar,et al.  Rule-based reasoning in connectionist networks , 1997 .

[56]  Roger Ratcliff,et al.  The comprehension processes and memory structures involved in anaphoric reference , 1980 .

[57]  Ron Sun,et al.  On Variable Binding in Connectionist Networks , 1992 .

[58]  M. Usher,et al.  Parallel Activation of Memories in an Oscillatory Neural Network , 1991, Neural Computation.

[59]  Andy Zuppann,et al.  A Connectionist Approach to Word Sense Disambiguation , 2003 .

[60]  J. Keenan,et al.  The effects of causal cohesion on comprehension and memory , 1984 .

[61]  E. Fetz,et al.  Coherent 25- to 35-Hz oscillations in the sensorimotor cortex of awake behaving monkeys. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[62]  Marius Usher,et al.  Visual synchrony affects binding and segmentation in perception , 1998, Nature.

[63]  A. Newell.  Unified Theories of Cognition , 1990 .

[64]  Graeme Hirst,et al.  Review of A connectionist approach to word sense disambiguation by Garrison W. Cottrell. Pitman and Morgan Kaufmann 1989. , 1990 .

[65]  Jordan B. Pollack,et al.  Recursive Distributed Representations , 1990, Artif. Intell..

[66]  D. Ballard,et al.  Connectionist models and their properties Cognitive Science , 2002 .

[67]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[68]  Marvin S. Cohen,et al.  Metarecognition in Time-Stressed Decision Making: Recognizing, Critiquing, and Correcting , 1996, Hum. Factors.

[69]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[70]  Paul Smolensky,et al.  Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1990, Artif. Intell..

[71]  John E. Hummel,et al.  Distributed representations of structure: A theory of analogical access and mapping. , 1997 .

[72]  J E Lisman,et al.  Storage of 7 +/- 2 short-term memories in oscillatory subcycles , 1995, Science.

[73]  Garrison W. Cottrell,et al.  From symbols to neurons: Are we there yet? , 1993, Behavioral and Brain Sciences.

[74]  Tj Sejnowski,et al.  Skeleton filters in the brain , 2014 .

[75]  Lokendra Shastri,et al.  Recruitment of binding and binding-error detector circuits via long-term potentiation , 1999, Neurocomputing.

[76]  D. R. Mani,et al.  Reflexive Reasoning with Multiple Instantiation in a Connectionist Reasoning System with a Type Hierarchy , 1993 .

[77]  Lokendra Shastri,et al.  From transient patterns to persistent structures: A model of episodic memory formation via cortico-hippocampal interactions , 2002 .

[78]  Joachim M. Buhmann,et al.  Pattern Segmentation in Associative Memory , 1990, Neural Computation.

[79]  Jacques Sougné,et al.  A Connectionist Model of Reflective Reasoning Using Temporal Properties of Node Firing , 1996 .