Self-organizing neural networks for universal learning and multimodal memory encoding

Learning and memory are two intertwined cognitive functions of the human brain. This paper shows how a family of biologically-inspired self-organizing neural networks, known as fusion Adaptive Resonance Theory (fusion ART), may provide a viable approach to realizing the learning and memory functions. Fusion ART extends the single-channel Adaptive Resonance Theory (ART) model to learn multimodal pattern associative mappings. As a natural extension of ART, various forms of fusion ART have been developed for a myriad of learning paradigms, ranging from unsupervised learning to supervised learning, semi-supervised learning, multimodal learning, reinforcement learning, and sequence learning. In addition, fusion ART models may be used for representing various types of memories, notably episodic memory, semantic memory and procedural memory. In accordance with the notion of embodied intelligence, such neural models thus provide a computational account of how an autonomous agent may learn and adapt in a real-world environment. The efficacy of fusion ART in learning and memory shall be discussed through various examples and illustrative case studies.

[1]  Wenwen Wang,et al.  Semantic Memory Modeling and Memory Interaction in Learning Agents , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[2]  Haibo He,et al.  Spatio–Temporal Memories for Machine Learning: A Long-Term Memory Organization , 2009, IEEE Transactions on Neural Networks.

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

[4]  John E. Laird,et al.  Extending Cognitive Architecture with Episodic Memory , 2007, AAAI.

[5]  Chunyan Miao,et al.  Modelling Autobiographical Memory Loss across Life Span , 2019, AAAI.

[6]  Ah-Hwee Tan,et al.  Adaptive Resonance Theory (ART) for Social Media Analytics , 2019, Advanced Information and Knowledge Processing.

[7]  E. Tulving.  How many memory systems are there , 1985 .

[8]  Ah-Hwee Tan,et al.  Cascade ARTMAP: integrating neural computation and symbolic knowledge processing , 1997, IEEE Trans. Neural Networks.

[9]  Jacek M. Zurada,et al.  Self-Organizing Neural Networks Integrating Domain Knowledge and Reinforcement Learning , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Stephen Grossberg,et al.  Intelligence Through Interaction: Towards a Unified Theory for Learning , 2007, ISNN.

[11]  Ah-Hwee Tan,et al.  Neural modeling of sequential inferences and learning over episodic memory , 2015, Neurocomputing.

[12]  Ah-Hwee Tan,et al.  Adaptive resonance associative map , 1995, Neural Networks.

[13]  E. Tulving,et al.  Episodic and semantic memory , 1972 .

[14]  M. Conway,et al.  The construction of autobiographical memories in the self-memory system. , 2000, Psychological review.

[15]  Ah-Hwee Tan,et al.  FALCON: a fusion architecture for learning, cognition, and navigation , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[16]  Dong Xu,et al.  Semi-Supervised Heterogeneous Fusion for Multimedia Data Co-Clustering , 2014, IEEE Transactions on Knowledge and Data Engineering.

[17]  Chrystopher L. Nehaniv,et al.  Comparing Different Control Architectures for Autobiographic Agents in Static Virtual Environments , 2003, IVA.

[18]  Ah-Hwee Tan,et al.  Self-organizing Neural Architecture for Reinforcement Learning , 2006, ISNN.

[19]  Ah-Hwee Tan,et al.  iFALCON: A neural architecture for hierarchical planning , 2012, Neurocomputing.

[20]  Ah-Hwee Tan,et al.  MyLife: An Online Personal Memory Album , 2015, 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT).

[21]  S. Grossberg,et al.  Towards a theory of the laminar architecture of cerebral cortex: computational clues from the visual system. , 2003, Cerebral cortex.

[22]  Chunyan Miao,et al.  Online Multimodal Co-indexing and Retrieval of Weakly Labeled Web Image Collections , 2015, ICMR.

[23]  T. Teyler,et al.  The hippocampal memory indexing theory. , 1986, Behavioral neuroscience.

[24]  Ah-Hwee Tan,et al.  Predictive neural networks for gene expression data analysis , 2005, Neural Networks.

[25]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[26]  Ah-Hwee Tan,et al.  Community Discovery in Social Networks via Heterogeneous Link Association and Fusion , 2014, SDM.

[27]  Ah-Hwee Tan,et al.  Adaptive computer-generated forces for simulator-based training , 2013, Expert Syst. Appl..

[28]  Wenwen Wang,et al.  Neural Modeling of Episodic Memory: Encoding, Retrieval, and Forgetting , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Ah-Hwee Tan,et al.  Self-organizing neural networks for learning air combat maneuvers , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[30]  Ah-Hwee Tan,et al.  Agent-Based Virtual Humans in Co-Space: An Evaluative Study , 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[31]  Wenwen Wang,et al.  Memory formation, consolidation, and forgetting in learning agents , 2012, AAMAS.

[32]  Ah-Hwee Tan,et al.  Predictive Adaptive Resonance Theory and Knowledge Discovery in Databases , 2000, PAKDD.

[33]  Thomas P. Caudell,et al.  A neural architecture for pattern sequence verification through inferencing , 1993, IEEE Trans. Neural Networks.

[34]  D. Rubin,et al.  Emotionally Charged Autobiographical Memories Across the Life Span: The Recall of Happy, Sad, Traumatic, and Involuntary Memories , 2002 .

[35]  S. Grossberg.  Adaptive Resonance Theory , 2006 .

[36]  Ah-Hwee Tan,et al.  Encoding and Recall of Spatio-Temporal Episodic Memory in Real Time , 2017, IJCAI.

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

[38]  L. Levine,et al.  Reminiscence as autobiographical memory: a catalyst for reminiscence theory development , 1998, Ageing and Society.

[39]  Ah-Hwee Tan,et al.  On Machine Learning Methods for Chinese Document Categorization , 2003, Applied Intelligence.

[40]  Ah-Hwee Tan,et al.  Direct Code Access in Self-Organizing Neural Networks for Reinforcement Learning , 2007, IJCAI.

[41]  Ah-Hwee Tan,et al.  Semi-supervised hierarchical clustering for personalized web image organization , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[42]  Ah-Hwee Tan,et al.  Towards autonomous behavior learning of non-player characters in games , 2016, Expert Syst. Appl..

[43]  Ah-Hwee Tan,et al.  Integrating Temporal Difference Methods and Self-Organizing Neural Networks for Reinforcement Learning With Delayed Evaluative Feedback , 2008, IEEE Transactions on Neural Networks.

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

[45]  Ah-Hwee Tan,et al.  Creating Autonomous Adaptive Agents in a Real-Time First-Person Shooter Computer Game , 2015, IEEE Transactions on Computational Intelligence and AI in Games.

[46]  Jong-Hwan Kim,et al.  Deep ART Neural Model for Biologically Inspired Episodic Memory and Its Application to Task Performance of Robots , 2018, IEEE Transactions on Cybernetics.

[47]  Stephen Grossberg,et al.  Adaptive pattern classification and universal recoding: II. Feedback, expectation, olfaction, illusions , 1976, Biological Cybernetics.

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

[49]  G. Ascoli,et al.  A simple neural network model of the hippocampus suggesting its pathfinding role in episodic memory retrieval. , 2005, Learning & memory.

[50]  Wenwen Wang,et al.  A self-organizing multi-memory system for autonomous agents , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

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

[52]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[53]  S. Grossberg.  How does the cerebral cortex work? Development, learning, attention, and 3-D vision by laminar circuits of visual cortex. , 2003, Behavioral and cognitive neuroscience reviews.