Working Memory Networks for Learning Temporal Order with Application to Three-Dimensional Visual Object Recognition

Working memory neural networks, called Sustained Temporal Order REcurrent (STORE) models, encode the invariant temporal order of sequential events in short-term memory (STM). Inputs to the networks may be presented with widely differing growth rates, amplitudes, durations, and interstimulus intervals without altering the stored STM representation. The STORE temporal order code is designed to enable groupings of the stored events to be stably learned and remembered in real time, even as new events perturb the system. Such invariance and stability properties are needed in neural architectures which self-organize learned codes for variable-rate speech perception, sensorimotor planning, or three-dimensional (3-D) visual object recognition. Using such a working memory, a self-organizing architecture for invariant 3-D visual object recognition is described. The new model is based on the model of Seibert and Waxman (1990a), which builds a 3-D representation of an object from a temporally ordered sequence of its two-dimensional (2-D) aspect graphs. The new model, called an ARTSTORE model, consists of the following cascade of processing modules: Invariant Preprocessor ART 2 STORE Model ART 2 Outstar Network.

[1]  J. Diederich.  Reasoning, learning and neuropsychological plausibility , 1993, Behavioral and Brain Sciences.

[2]  Michael A. Arbib,et al.  Complex temporal sequence learning based on short-term memory , 1990 .

[3]  R. Atkinson,et al.  The control of short-term memory. , 1971, Scientific American.

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

[5]  John E. Hummel,et al.  Distributing structure over time , 1993, Behavioral and Brain Sciences.

[6]  Richard Rohwer,et al.  Useful ideas for exploiting time to engineer representations , 1993, Behavioral and Brain Sciences.

[7]  Georg Dorffner,et al.  Connectionism and syntactic binding of concepts , 1993, Behavioral and Brain Sciences.

[8]  Malcolm Bauer,et al.  Plausible inference and implicit representation , 1993, Behavioral and Brain Sciences.

[9]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[10]  David S. Touretzky,et al.  Should first-order logic be neurally plausible? , 1993, Behavioral and Brain Sciences.

[11]  Allen M. Waxman,et al.  Learning and Recognizing 3D Objects from Multiple Views in a Neural System , 1992 .

[12]  J. Garson.  Must we solve the binding problem in neural hardware? , 1993, Behavioral and Brain Sciences.

[13]  Personnaz,et al.  Storage and retrieval of complex sequences in neural networks. , 1988, Physical review. A, General physics.

[14]  S. Grossberg.  Some Networks that can Learn, Remember, and Reproduce any Number of Complicated Space-time , 1970 .

[15]  S. Grossberg.  Self-organizing neural models of categorization, inference and synchrony , 1993, Behavioral and Brain Sciences.

[16]  John A. Barnden,et al.  Time phases, pointers, rules and embedding , 1993, Behavioral and Brain Sciences.

[17]  I. Tsuda.  Dynamic-binding theory is not plausible without chaotic oscillation , 1993, Behavioral and Brain Sciences.

[18]  R. Eckhorn.  Dynamic bindings by real neurons: Arguments from physiology, neural network models and information theory , 1993, Behavioral and Brain Sciences.

[19]  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.

[20]  Allen M. Waxman,et al.  Learning Aspect Graph Representations from View Sequences , 1989, NIPS.

[21]  Stellan Ohlsson,et al.  Psychological implications of the synchronicity hypothesis , 1993, Behavioral and Brain Sciences.

[22]  Stephen Grossberg,et al.  Neural dynamics of adaptive sensory-motor control , 1986 .

[23]  J. Feldman.  Toward a unified behavioral and brain science , 1993, Behavioral and Brain Sciences.

[24]  S Grossberg,et al.  Masking fields: a massively parallel neural architecture for learning, recognizing, and predicting multiple groupings of patterned data. , 1987, Applied optics.

[25]  S. Grossberg,et al.  Pattern Recognition by Self-Organizing Neural Networks , 1991 .

[26]  P. Hampson.  Rule acquisition and variable binding: Two sides of the same coin , 1993, Behavioral and Brain Sciences.

[27]  Alice F. Healy,et al.  Separating item from order information in short-term memory , 1974 .

[28]  Istvan S. N. Berkeley,et al.  Making a middling mousetrap , 1993, Behavioral and Brain Sciences.

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

[30]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[31]  S. Grossberg,et al.  Spiking threshold and overarousal effects in serial learning , 1971 .

[32]  Stephen Grossberg,et al.  A Theory of Human Memory: Self-Organization and Performance of Sensory-Motor Codes, Maps, and Plans , 1982 .

[33]  M. Oaksford,et al.  Computational and biological constraints in the psychology of reasoning , 1993, Behavioral and Brain Sciences.

[34]  E. Koerner.  Synchronization and cognitive carpentry: From systematic structuring to simple reasoning , 1993, Behavioral and Brain Sciences.

[35]  S. Grossberg,et al.  Neural dynamics of attention switching and temporal-order information in short-term memory , 1988, Memory & cognition.

[36]  Paul R. Cooper,et al.  Could static binding suffice? , 1993, Behavioral and Brain Sciences.

[37]  Michael C. Seibert,et al.  Neural networks for machine vision: learning three-dimensional object representations , 1991 .

[38]  A. J. Mistlin,et al.  Visual neurones responsive to faces , 1987, Trends in Neurosciences.

[39]  S. Thorpe.  Temporal synchrony and the speed of visual processing , 1993, Behavioral and Brain Sciences.

[40]  Lokendra Shastri,et al.  A step toward modeling reflexive reasoning , 1993, Behavioral and Brain Sciences.

[41]  S. Grossberg.  Behavioral Contrast in Short Term Memory: Serial Binary Memory Models or Parallel Continuous Memory Models? , 1978 .

[42]  David L. Martin.  Reflections on reflexive reasoning , 1993, Behavioral and Brain Sciences.

[43]  R. Futami,et al.  A neural network model of short-term sequence memory , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[44]  Günther Palm,et al.  Making reasoning more reasonable: Event-coherence and assemblies , 1993, Behavioral and Brain Sciences.

[45]  Steffen Hölldobler.  On the artificial intelligence paradox , 1993, Behavioral and Brain Sciences.

[46]  S. Sloman.  Do simple associations lead to systematic reasoning? , 1993, Behavioral and Brain Sciences.

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

[48]  G. Sperling,et al.  Attention gating in short-term visual memory. , 1986, Psychological review.

[49]  S Grossberg,et al.  Some nonlinear networks capable of learning a spatial pattern of arbitrary complexity. , 1968, Proceedings of the National Academy of Sciences of the United States of America.

[50]  W. Estes,et al.  Item and order information in short-term memory: Evidence for multilevel perturbation processes. , 1981 .

[51]  Gutfreund,et al.  Processing of temporal sequences in neural networks. , 1988, Physical review letters.

[52]  Graeme S. Halford,et al.  Competing, or perhaps complementary, approaches to the dynamic-binding problem, with similar capacity limitations , 1993, Behavioral and Brain Sciences.

[53]  Roger Ratcliff,et al.  A Theory of Memory Retrieval. , 1978 .

[54]  Stanley Munsat.  What we know and the LTKB , 1993, Behavioral and Brain Sciences.

[55]  S. Grossberg.  Contour Enhancement , Short Term Memory , and Constancies in Reverberating Neural Networks , 1973 .