Brain-Like Emergent Temporal Processing: Emergent Open States

Informed by brain anatomical studies, we present the developmental network (DN) theory on brain-like temporal information processing. The states of the brain are at its effector end, emergent and open. A finite automaton (FA) is considered an external symbolic model of brain's temporal behaviors, but the FA uses handcrafted states and is without “internal” representations. The term “internal” means inside the network “skull.” Using action-based state equivalence and the emergent state representations, the time driven processing of DN performs state-based abstraction and state-based skill transfer. Each state of DN, as a set of actions, is openly observable by the external environment (including teachers). Thus, the external environment can teach the state at every frame time. Through incremental learning and autonomous practice, the DN lumps (abstracts) infinitely many temporal context sequences into a single equivalent state. Using this state equivalence, a skill learned under one sequence is automatically transferred to other infinitely many state-equivalent sequences in the future without the need for explicit learning. Two experiments are shown as examples: The experiments for video processing showed almost perfect recognition rates in disjoint tests. The experiment for text language, using corpora from the Wall Street Journal, treated semantics and syntax in a unified interactive way.

[1]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Juyang Weng,et al.  A 5-chunk developmental brain-mind network model for multiple events in complex backgrounds , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[3]  John E. Schlerf,et al.  Dedicated and intrinsic models of time perception , 2008, Trends in Cognitive Sciences.

[4]  Dileep George,et al.  Towards a Mathematical Theory of Cortical Micro-circuits , 2009, PLoS Comput. Biol..

[5]  D. J. Felleman,et al.  Distributed hierarchical processing in the primate cerebral cortex. , 1991, Cerebral cortex.

[6]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[7]  Juyang Weng,et al.  2008 Special issue , 2008 .

[8]  A. M. Burton,et al.  100% Accuracy in Automatic Face Recognition , 2008, Science.

[9]  J. Cleary,et al.  \self-organized Language Modeling for Speech Recognition". In , 1997 .

[10]  Juyang Weng,et al.  Modeling dopamine and serotonin systems in a visual recognition network , 2011, The 2011 International Joint Conference on Neural Networks.

[11]  Juyang Weng,et al.  Three theorems: Brain-like networks logically reason and optimally generalize , 2011, The 2011 International Joint Conference on Neural Networks.

[12]  C. Koch,et al.  An oscillation-based model for the neuronal basis of attention , 1993, Vision Research.

[13]  Giovanni Soda,et al.  Unified Integration of Explicit Knowledge and Learning by Example in Recurrent Networks , 1995, IEEE Trans. Knowl. Data Eng..

[14]  John F. Kolen,et al.  Simple Stable Encodings of FiniteState Machines in Dynamic Recurrent Networks , 2001 .

[15]  Risto Miikkulainen,et al.  Computational Maps in the Visual Cortex , 2005 .

[16]  C. Lee Giles,et al.  Constructing deterministic finite-state automata in recurrent neural networks , 1996, JACM.

[17]  L. Abbott,et al.  Extending the effects of spike-timing-dependent plasticity to behavioral timescales. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Robert Desimone,et al.  Parallel and Serial Neural Mechanisms for Visual Search in Macaque Area V4 , 2005, Science.

[19]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[20]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  U. Karmarkar,et al.  Timing in the Absence of Clocks: Encoding Time in Neural Network States , 2007, Neuron.

[22]  Fei-Fei Li,et al.  Modeling mutual context of object and human pose in human-object interaction activities , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  R. Gardner,et al.  Teaching sign language to a chimpanzee. , 1969, Science.

[24]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[25]  Jan C. Wiemer,et al.  The Time-Organized Map Algorithm: Extending the Self-Organizing Map to Spatiotemporal Signals , 2003, Neural Computation.

[26]  George A. Miller,et al.  CYC, WordNet, and EDR: critiques and responses , 1995, CACM.

[27]  Aaron R. Seitz,et al.  Laminar development of receptive fields, maps and columns in visual cortex: the coordinating role of the subplate. , 2003, Cerebral cortex.

[28]  T. Sejnowski,et al.  Irresistible environment meets immovable neurons , 1997, Behavioral and Brain Sciences.

[29]  Juyang Weng,et al.  Complex text processing by the temporal context machines , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[30]  M. Sur,et al.  Patterning and Plasticity of the Cerebral Cortex , 2005, Science.

[31]  M. Sur,et al.  Development and plasticity of cortical areas and networks , 2001, Nature Reviews Neuroscience.

[32]  John R. Anderson,et al.  Rules of the Mind , 1993 .

[33]  Marvin Minsky,et al.  Logical Versus Analogical or Symbolic Versus Connectionist or Neat Versus Scruffy , 1991, AI Mag..

[34]  J. Piaget.  The construction of reality in the child , 1954 .

[35]  M M Merzenich,et al.  Temporal information transformed into a spatial code by a neural network with realistic properties , 1995, Science.

[36]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[37]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[38]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[39]  Gary Cantor,et al.  On the Relationship Between Implicit and Explicit Modes in the Learning of a Complex Rule Structure , 1980 .

[40]  Herbert Jaeger,et al.  Adaptive Nonlinear System Identification with Echo State Networks , 2002, NIPS.

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

[42]  Juyang Weng,et al.  Topographic Class Grouping with applications to 3D object recognition , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[43]  Pieter R. Roelfsema,et al.  Attention-Gated Reinforcement Learning of Internal Representations for Classification , 2005, Neural Computation.

[44]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[45]  S. Grossberg,et al.  Contrast-sensitive perceptual grouping and object-based attention in the laminar circuits of primary visual cortex , 2000, Vision Research.

[46]  Giovanni Soda,et al.  Representation of finite state automata in Recurrent Radial Basis Function networks , 2004, Machine Learning.

[47]  B. Raman,et al.  Sparse odor representation and olfactory learning , 2008, Nature Neuroscience.

[48]  Juyang Weng,et al.  Dually Optimal Neuronal Layers: Lobe Component Analysis , 2009, IEEE Transactions on Autonomous Mental Development.

[49]  J. Weng,et al.  Optimal In-Place Self-Organization for Cortical Development : Limited Cells , Sparse Coding and Cortical Topography , 2006 .

[50]  Jun Tani,et al.  How Hierarchical Control Self-organizes in Artificial Adaptive Systems , 2005, Adapt. Behav..

[51]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[52]  J. Elman,et al.  Rethinking Innateness: A Connectionist Perspective on Development , 1996 .

[53]  Deva Ramanan,et al.  Learning to parse images of articulated bodies , 2006, NIPS.

[54]  Edward M. Callaway,et al.  Feedforward, feedback and inhibitory connections in primate visual cortex , 2004, Neural Networks.

[55]  Ida J. Stockman.  Movement and Action in Learning and Development: Clinical Implications for Pervasive Developmental Disorders , 2004 .

[56]  J. Iverson.  Developing language in a developing body: the relationship between motor development and language development. , 2010, Journal of child language.

[57]  U. Rieder,et al.  Markov Decision Processes , 2010 .

[58]  Juyang Weng,et al.  Where-what network-4: The effect of multiple internal areas , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[59]  Juyang Weng,et al.  Symbolic Models and Emergent Models: A Review , 2012, IEEE Transactions on Autonomous Mental Development.

[60]  M. Domjan.  The principles of learning and behavior , 1982 .

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

[62]  E. Callaway.  Local circuits in primary visual cortex of the macaque monkey. , 1998, Annual review of neuroscience.

[63]  Noam Chomsky,et al.  Rules and Representations , 1982 .

[64]  A. Brueckner.  Brains in a Vat , 1986 .

[65]  G. Bi,et al.  Synaptic modification by correlated activity: Hebb's postulate revisited. , 2001, Annual review of neuroscience.

[66]  Juyang Weng,et al.  WWN-2: A biologically inspired neural network for concurrent visual attention and recognition , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[67]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[68]  Juyang Weng,et al.  Motor initiated expectation through top-down connections as abstract context in a physical world , 2008, 2008 7th IEEE International Conference on Development and Learning.

[69]  Juyang Weng,et al.  Temporal context as cortical spatial codes , 2009, 2009 International Joint Conference on Neural Networks.

[70]  Frank S. Moyer.  CRITIQUES AND RESPONSES , 1998 .

[71]  James L. McClelland,et al.  Autonomous Mental Development by Robots and Animals , 2001, Science.

[72]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[73]  Daniel Oblinger.  Toward a Computational Model of Transfer , 2011, AI Mag..

[74]  W. Lovejoy.  A survey of algorithmic methods for partially observed Markov decision processes , 1991 .

[75]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[76]  D. Buonomano,et al.  The neural basis of temporal processing. , 2004, Annual review of neuroscience.

[77]  D. Luenberger.  Optimization by Vector Space Methods , 1968 .

[78]  S. Engel.  Thought and Language , 1964 .

[79]  K. Nelson,et al.  Languages and Language-Related Skills in Deaf and Hearing Children , 2013 .

[80]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[81]  Ahmad Emami,et al.  A Neural Syntactic Language Model , 2005, Machine Learning.

[82]  E. Callaway,et al.  Contributions of individual layer 6 pyramidal neurons to local circuitry in macaque primary visual cortex , 1996, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[83]  Larry S. Davis,et al.  Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[84]  M. Domjan.  The principles of learning and behavior, 4th ed. , 1998 .

[85]  Juyang Weng,et al.  Neuromorphic motivated systems , 2011, The 2011 International Joint Conference on Neural Networks.

[86]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[87]  Paul J. Werbos,et al.  The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting , 1994 .

[88]  G. Deco,et al.  A hierarchical neural system with attentional top–down enhancement of the spatial resolution for object recognition , 2000, Vision Research.

[89]  Juyang Weng,et al.  Why Have We Passed “ Neural Networks Do Not Abstract Well ” ? , 2011 .

[90]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[91]  Dina Feitelson.  Facts and Fads in Beginning Reading: A Cross-Language Perspective , 1988 .

[92]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[93]  Bernt Schiele,et al.  Pictorial structures revisited: People detection and articulated pose estimation , 2009, CVPR.

[94]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

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

[96]  Juyang Weng,et al.  Online-learning and Attention-based Approach to Obstacle Avoidance Using a Range Finder , 2007, J. Intell. Robotic Syst..

[97]  Juyang Weng,et al.  Where-What Network 5: Dealing with scales for objects in complex backgrounds , 2011, The 2011 International Joint Conference on Neural Networks.

[98]  Michael I. Jordan.  Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .

[99]  E. Rolls,et al.  A Neurodynamical cortical model of visual attention and invariant object recognition , 2004, Vision Research.

[100]  R. Sun,et al.  The interaction of the explicit and the implicit in skill learning: a dual-process approach. , 2005, Psychological review.

[101]  Juyang Weng,et al.  On developmental mental architectures , 2007, Neurocomputing.

[102]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[103]  James L. McClelland,et al.  Connectionist models of development , 2003 .

[104]  Risto Miikkulainen,et al.  Self-organization of hierarchical visual maps with feedback connections , 2006, Neurocomputing.

[105]  Juyang Weng,et al.  Where What Network 3 : Developmental Top-Down Attention with Multiple Meaningful Foregrounds , 2010 .

[106]  Juyang Weng.  Brain Model For Developmental Robots : The Spatial Brain for Any Temporal Lengths , 2010 .

[107]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[108]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[109]  Noam Chomsky,et al.  Rules and representations , 1980, Behavioral and Brain Sciences.

[110]  Lawrence R. Rabiner,et al.  Toward Vision 2001: Voice and audio processing considerations , 1995, AT&T Technical Journal.

[111]  Y. Dan,et al.  Spike timing-dependent plasticity: from synapse to perception. , 2006, Physiological reviews.

[112]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[113]  Juyang Weng,et al.  Where-what network 1: “Where” and “what” assist each other through top-down connections , 2008, 2008 7th IEEE International Conference on Development and Learning.

[114]  Jun Tani,et al.  Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment , 2008, PLoS Comput. Biol..

[115]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.