Programme Overview
Detailed Programme

Computational Neuroscience and Neurodynamics (CNN)

CHAIR: KEVIN WARWICK

Tuesday, March 22nd, 11h00-12h40

Paper ID   Title
   
CNN-1 Cortical Modulation of Synaptic Efficacies through Norepinephrine
CNN-2 Associative Memories with Small World Connectivity
CNN-3 A Memory-Based Reinforcement Learning Model Utilizing Macro-Actions
CNN-4 A Biologically Motivated Classifier that Preserves Implicit Relationship Information in Layered Networks
CNN-5 Large Scale Hetero-Associative Networks with Very High Classification Ability and Attractor Discrimination Consisting of Cumulative-Learned 3-Layer Neural Networks


CNN-1
 
Title: Cortical Modulation of Synaptic Efficacies through Norepinephrine
Author(s): O. Hoshino
Abstract: I propose a norepinephrine- (NE-) neuromodulatory system, which I call “enhanced-excitatory and enhanced-inhibitory (E-E/E-I) system”. The E-E/E-I system enhanced excitatory and inhibitory synaptic connections between cortical cells, modified their ongoing background activity, and influenced subsequent cognitive neuronal processing. When stimulated with sensory features, cognitive performance of neurons, signal-to-noise (S/N) ratio, was greatly enhanced, for which one of the three possible S/N enhancement schemes operated under the E-E/E-I system, namely; i) signal enhancement more than noise increase, ii) signal enhancement and noise reduction, and iii) noise reduction more than signal decrease. When a weaker (or subthreshold) stimulus was presented, the scheme (ii) effectively enhanced S/N ratio, whereas the scheme (iii) was effective for enhancing stronger stimuli. I suggest that a release of NE into cortical areas may modify their background neuronal activity, whereby cortical neurons can effectively respond to a variety of external sensory stimuli.


CNN-2
 
Title: Associative Memories with Small World Connectivity
Author(s): Neil Davey,
Lee Calcraft,
Rod Adams
Abstract: In this paper we report experiments designed to find the relationship between the different parameters of sparsely connected networks of perceptrons with small world connectivity patterns, acting as associative memories.


CNN-3
 
Title: A Memory-Based Reinforcement Learning Model Utilizing Macro-Actions
Author(s): Makoto Murata,
Seiichi Ozawa
Abstract: One of the difficulties in reinforcement learning is that an optimal policy is acquired through enormous trials. As a solution to reduce waste explorations in learning, recently the exploitation of macro-actions has been focused. In this paper, we propose a memory-based reinforcement learning model in which macro-actions are generated and exploited usefully. Through the experiments for two standard tasks, we confirmed that our proposed method can decrease waste explorations especially in the early training stage. This property contributes to enhancing training efficiency in RL tasks.


CNN-4
 
Title: A Biologically Motivated Classifier that Preserves Implicit Relationship Information in Layered Networks
Author(s): Charles C. Peck,
James Kozloski,
Guillermo A. Cecchi,
A. Ravishankar Rao
Abstract: A fundamental problem with layered neural networks is the loss of information about the relationships among features in the input space and relationships inferred by higher order classifiers. Information about these relationships is required to solve problems such as discrimination of simultaneously presented objects and discrimination of feature components. We propose a biologically motivated model for a classifier that preserves this information. When composed into classification networks, we show that the classifier propagates and aggregates information about feature relationships. We discuss how the model should be capable of segregating this information for the purpose of object discrimination and aggregating multiple feature components for the purpose of feature component discrimination.


CNN-5
 
Title: Large Scale Hetero-Associative Networks with Very High Classification Ability and Attractor Discrimination Consisting of Cumulative-Learned 3-Layer Neural Networks
Author(s): Yohtaro Yatsuzuka, Yo Ho
Abstract: We propose a hetero-associative network consisting of a cumulative-learned forward 3-layer neural network and a backward 3-layer neural network, and a hetero-tandem associative network. The hetero-tandem associative network has a spindle type single cyclic-associative network with cumulative learning subsequent the hetero-associative network in tandem. These hetero-associative networks have high of classification and recognition performance, as well as rapid attractor absorption. Consecutive codification of outputs in the forward network was found to produce no spurious attractors, and for coarse codification the converged attractors can be easily identified as training or spurious attractors. Cumulative learning with prototypes and additive training data adjacent to them can also drastically improve the associative performance of both the spindle single cyclic-associative and hetero-tandem associative networks.