Novelty estimation in developmental networks: Acetylcholine and norepinephrine

The receiver operating characteristic (ROC) curve has been widely applied to classifiers to show how the threshold value for acceptance changes the true positive rate and the false positive rate of the detection jointly. However, it is largely unknown how a biological brain autonomously selects a confidence value for each detection case. In the reported work, we investigated this issue based on the class of Developmental Networks (DNs) which have a power of abstraction similar to symbolic finite automata (FA) but all the DN's representations are emergent (i.e., numeric from the physical world and non-symbolic). Our theory is based on two types of neurotransmitters: Acetylcholine (Ach) and Norepinephrine (NE). Inspired by studies that proposed Ach and NE represent uncertainty and unpredicted uncertainty, respectively, we model how a DN uses Ach and NE to allow neurons to collectively decide acceptance or rejection by estimated novelty based on past experience, instead of using a single threshold value. This is a neural network, distributed, incremental, automatic version of ROC.

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

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

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

[4]  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).

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

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

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

[8]  Sameer Singh,et al.  An approach to novelty detection applied to the classification of image regions , 2004, IEEE Transactions on Knowledge and Data Engineering.

[9]  Angela J. Yu,et al.  Uncertainty, Neuromodulation, and Attention , 2005, Neuron.

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

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

[12]  Eugene M. Izhikevich,et al.  Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting , 2006 .

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

[14]  Juyang Weng,et al.  Inherent Value Systems for Autonomous Mental Development , 2007, Int. J. Humanoid Robotics.

[15]  Sameer Singh,et al.  Novelty detection: a review - part 2: : neural network based approaches , 2003, Signal Process..

[16]  Xiao Huang,et al.  Novelty and Reinforcement Learning in the Value System of Developmental Robots , 2002 .

[17]  James L. McClelland,et al.  Semantic Cognition: A Parallel Distributed Processing Approach , 2004 .

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

[19]  J. Tenenbaum,et al.  Theory-based Bayesian models of inductive learning and reasoning , 2006, Trends in Cognitive Sciences.

[20]  Risto Miikkulainen,et al.  Intrusion Detection with Neural Networks , 1997, NIPS.

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

[22]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

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

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