STORE working memory networks for storage and recall of arbitrary temporal sequences

Neural network models of working memory, called “sustained temporal order recurrent” (STORE) models, are described. They encode the invariant temporal order of sequential events in short-term memory (STM) in a way that mimics cognitive data about working memory, including primacy, recency, and bowed order and error gradients. As new items are presented, the pattern of previously stored items remains invariant in the sense that relative activations remain constant through time. This invariant temporal order code enables all possible groupings of sequential events to be stably learned and remembered in real time, even as new events perturb the system. Such competence is needed to design self-organizing temporal recognition and planning systems in which any subsequence of events may need to be categorized in order to control and predict future behavior or external events. STORE models show how arbitrary event sequences may be invariantly stored, including repeated events. A preprocessor interacts with the working memory to represent event repeats in spatially separate locations. It is shown why at least two processing levels are needed to invariantly store events presented with variable durations and interstimulus intervals. It is also shown how network parameters control the type and shape of primacy, recency, or bowed temporal order gradients that will be stored.

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

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

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

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

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

[6]  B H Repp,et al.  Perceptual integration of acoustic cues for stop, fricative, and affricate manner. , 1978, Journal of experimental psychology. Human perception and performance.

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

[8]  A.G. Lozowski,et al.  Processing temporal sequences , 2002, The 2002 45th Midwest Symposium on Circuits and Systems, 2002. MWSCAS-2002..

[9]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

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

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

[12]  Stephen Grossberg,et al.  CHAPTER 6 – The Adaptive Self-organization of Serial Order in Behavior: Speech, Language, and Motor Control* , 1986 .

[13]  William S. Maki,et al.  Item and order information in spatial memory. , 1984 .

[14]  S. Grossberg.  Some Networks That Can Learn, Remember, and Reproduce any Number of Complicated Space-Time Patterns, I , 1969 .

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

[16]  A. Liberman,et al.  Some effects of later-occurring information on the perception of stop consonant and semivowel , 1979, Perception & psychophysics.

[17]  Stephen Grossberg,et al.  Variable Rate Working Memories for Phonetic Categorization and Invariant Speech Perception , 1993 .

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

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

[20]  S. Grossberg,et al.  Working Memory Networks for Learning Temporal Order, with Application to 3-D Visual Object Recognition , 1991 .

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

[22]  S. Grossberg,et al.  A self-organizing neural network for supervised learning, recognition, and prediction , 1992, IEEE Communications Magazine.

[23]  Stephen Grossberg,et al.  Neural dynamics of word recognition and recall: attentional priming, learning, and resonance. , 1986, Psychology Review.

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

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

[26]  B. Repp.  Bidirectional contrast effects in the perception of VC-CV sequences , 1983, Perception & psychophysics.

[27]  Stephen Grossberg,et al.  Working Memory Networks for Learning Temporal Order with Application to Three-Dimensional Visual Object Recognition , 1992, Neural Computation.

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

[29]  Daniel Bullock,et al.  A neural network model of serial order recall from short-term memory , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[30]  S. Grossberg.  Studies of mind and brain : neural principles of learning, perception, development, cognition, and motor control , 1982 .

[31]  Stephen Grossberg,et al.  Working memory networks for learning multiple groupings of temporally ordered events: applications to 3-D visual object recognition , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[32]  Stephen Grossberg,et al.  Vector associative maps: Unsupervised real-time error-based learning and control of movement trajectories , 1991, Neural Networks.

[33]  Michael I. Jordan.  Serial Order: A Parallel Distributed Processing Approach , 1997 .

[34]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

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

[36]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[37]  B H Repp,et al.  Perception of intervocalic stop consonants: the contributions of closure duration and formant transitions. , 1983, The Journal of the Acoustical Society of America.

[38]  Stephen Grossberg,et al.  Neural dynamics of speech and language coding: developmental programs, perceptual grouping, and competition for short-term memory. , 1986, Human neurobiology.

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

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

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

[42]  S. Grossberg.  The Adaptive Self-Organization of Serial Order in Behavior: Speech, Language, And Motor Control , 1987 .