A Neural Network of Adaptively Timed Reinforcement Learning and Hippocampal Dynamics

A neural model is described of how adaptively timed reinforcement learning occurs. The adaptive timing circuit is suggested to exist in the hippocampus, and to involve convergence of dentate granule cells on CA3 pyramidal cells, and NMDA receptors. This circuit forms part of a model neural system for the coordinated control of recognition learning, reinforcement learning, and motor learning, whose properties clarify how an animal can learn to acquire a delayed reward. Behavioral and neural data are summarized in support of each processing stage of the system. The relevant anatomical sites are in thalamus, neocortex, hippocampus, hypothalamus, amygdala, and cerebellum. Cerebellar influences on motor learning are distinguished from hippocampal influences on adaptive timing of reinforcement learning. The model simulates how damage to the hippocampal formation disrupts adaptive timing, eliminates attentional blocking, and causes symptoms of medial temporal amnesia. It suggests how normal acquisition of subcortical emotional conditioning can occur after cortical ablation, even though extinction of emotional conditioning is retarded by cortical ablation. The model simulates how increasing the duration of an unconditioned stimulus increases the amplitude of emotional conditioning, but does not change adaptive timing; and how an increase in the intensity of a conditioned stimulus "speeds up the clock", but an increase in the intensity of an unconditioned stimulus does not. Computer simulations of the model fit parametric conditioning data, including a Weber law property and an inverted U property. Both primary and secondary adaptively timed conditioning are simulated, as are data concerning conditioning using multiple interstimulus intervals (ISIs), gradually or abruptly changing ISis, partial reinforcement, and multiple stimuli that lead to time-averaging of responses. Neurobiologically testable predictions are made to facilitate further tests of the model.

A Neural Network Realization of Fuzzy ART

A neural network realization of the fuzzy Adaptive Resonance Theory (ART) algorithm is described. Fuzzy ART is capable of rapid stable learning of recognition categories in response to arbitrary sequences of analog or binary input patterns. Fuzzy ART incorporates computations from fuzzy set theory into the ART 1 neural network, which learns to categorize only binary input patterns, thus enabling the network to learn both analog and binary input patterns. In the neural network realization of fuzzy ART, signal transduction obeys a path capacity rule. Category choice is determined by a combination of bottom-up signals and learned category biases. Top-down signals impose upper bounds on feature node activations.

An Integrated Neural Network-Event-Related Potentials Model of Temporal and Probability Context Effects on Event Categorization

We present a neural network that adapts and integrates several preexisting or new modules to categorize events in short term memory (STM), encode temporal order in working memory, evaluate timing and probability context in medium and long term memory. The model shows how processed contextual information modulates event recognition and categorization, focal attention and incentive motivation. The model is based on a compendium of Event Related Potentials (ERPs) and behavioral results either collected by the authors or compiled from the classical ERP literature. Its hallmark is, at the functional level, the interplay of memory registers endowed with widely different dynamical ranges, and at the structural level, the attempt to relate the different modules to known anatomical structures.

Dynamic Programming for Optimal Control of Set-Up Scheduling with Neural Network Modifications

This paper demonstrates an optimal control solution to change of machine set-up scheduling based on dynamic programming average cost per stage value iteration as set forth by Cararnanis et. al. [2] for the 2D case. The difficulty with the optimal approach lies in the explosive computational growth of the resulting solution. A method of reducing the computational complexity is developed using ideas from biology and neural networks. A real time controller is described that uses a linear-log representation of state space with neural networks employed to fit cost surfaces.

A Self-Organizing Neural Network Model for Redundant Sensory-Motor Control, Motor Equivalence, and Tool Use

A neural network is introduced which provides a solution of the classical motor equivalence problem, whereby many different joint configurations of a redundant manipulator can all be used to realize a desired trajectory in 3-D space. To do this, the network self-organizes a mapping from motion directions in 3-D space to velocity commands in joint space. Computer simulations demonstrate that, without any additional learning, the network can generate accurate movement commands that compensate for variable tool lengths, clamping of joints, distortions of visual input by a prism, and unexpected limb perturbations. Blind reaches have also been simulated.

A What-and-Where Neural Network for Invariant Image Preprocessing

A feedforward neural network for invariant image preprocessing is proposed that represents the position1 orientation and size of an image figure (where it is) in a multiplexed spatial map. This map is used to generate an invariant representation of the figure that is insensitive to position1 orientation, and size for purposes of pattern recognition (what it is). A multiscale array of oriented filters followed by competition between orientations and scales is used to define the Where filter.

A Neural Network for Synthesizing the Pitch of an Acoustic Source

This article describes a neural network model capable of generating a spatial representation of the pitch of an acoustic source. Pitch is one of several auditory percepts used by humans to separate multiple sound sources in the environment from each other. The model provides a neural instantiation of a type of "harmonic sieve". It is capable of quantitatively simulating a large body of psychoacoustical data, including new data on octave shift perception.

Construction of Neural Network Classification Expert Systems Using Switching Theory Algorithms

A new family of neural network architectures is presented. This family of architectures solves the problem of constructing and training minimal neural network classification expert systems by using switching theory. The primary insight that leads to the use of switching theory is that the problem of minimizing the number of rules and the number of IF statements (antecedents) per rule in a neural network expert system can be recast into the problem of minimizing the number of digital gates and the number of connections between digital gates in a Very Large Scale Integrated (VLSI) circuit. The rules that the neural network generates to perform a task are readily extractable from the network's weights and topology. Analysis and simulations on the Mushroom database illustrate the system's performance.

A Neural Network Model of Spatio-Temporal Pattern Recognition, Recall and Timing

This paper describes the design of a self~organizing, hierarchical neural network model of unsupervised serial learning. The model learns to recognize, store, and recall sequences of unitized patterns, using either short-term memory (STM) or both STM and long-term memory (LTM) mechanisms. Timing information is learned and recall {both from STM and from LTM) is performed with a learned rhythmical structure. The network, bearing similarities with ART (Carpenter & Grossberg 1987a), learns to map temporal sequences to unitized patterns, which makes it suitable for hierarchical operation. It is therefore capable of self-organizing codes for sequences of sequences. The capacity is only limited by the number of nodes provided. Selected simulation results are reported to illustrate system properties.

Equilibria and Dynamics of a Neural Network Model for Opponent Muscle Control

One of the advantages of biological skeleto-motor systems is the opponent muscle design, which in principle makes it possible to achieve facile independent control of joint angle and joint stiffness. Prior analysis of equilibrium states of a biologically-based neural network for opponent muscle control, the FLETE model, revealed that such independent control requires specialized interneuronal circuitry to efficiently coordinate the opponent force generators. In this chapter, we refine the FLETE circuit variables specification and update the equilibrium analysis. We also incorporate additional neuronal circuitry that ensures efficient opponent force generation and velocity regulation during movement.

A Neural Network Model for Cursive Script Production

This article describes a neural network model, called the VITEWRITE model, for generating handwriting movements. The model consists of a sequential controller, or motor program, that interacts with a trajectory generator to move a. hand with redundant degrees of freedom. The neural trajectory generator is the Vector Integration to Endpoint (VITE) model for synchronous variable-speed control of multijoint movements. VITE properties enable a simple control strategy to generate complex handwritten script if the hand model contains redundant degrees of freedom. The proposed controller launches transient directional commands to independent hand synergies at times when the hand begins to move, or when a velocity peak in a given synergy is achieved. The VITE model translates these temporally disjoint synergy commands into smooth curvilinear trajectories among temporally overlapping synergetic movements. The separate "score" of onset times used in most prior models is hereby replaced by a self-scaling activity-released "motor program" that uses few memory resources, enables each synergy to exhibit a unimodal velocity profile during any stroke, generates letters that are invariant under speed and size rescaling, and enables effortless. connection of letter shapes into words. Speed and size rescaling are achieved by scalar GO and GRO signals that express computationally simple volitional commands. Psychophysical data concerning band movements, such as the isochrony principle, asymmetric velocity profiles, and the two-thirds power law relating movement curvature and velocity arise as emergent properties of model interactions.

Neural network analysis identifies scaffold properties necessary for in vitro chondrogenesis in elastin-like polypeptide biopolymer scaffolds.

The successful design of biomaterial scaffolds for articular cartilage tissue engineering requires an understanding of the impact of combinations of material formulation parameters on diverse and competing functional outcomes of biomaterial performance. This study sought to explore the use of a type of unsupervised artificial network, a self-organizing map, to identify relationships between scaffold formulation parameters (crosslink density, molecular weight, and concentration) and 11 such outcomes (including mechanical properties, matrix accumulation, metabolite usage and production, and histological appearance) for scaffolds formed from crosslinked elastin-like polypeptide (ELP) hydrogels. The artificial neural network recognized patterns in functional outcomes and provided a set of relationships between ELP formulation parameters and measured outcomes. Mapping resulted in the best mean separation amongst neurons for mechanical properties and pointed to crosslink density as the strongest predictor of most outcomes, followed by ELP concentration. The map also grouped formulations together that simultaneously resulted in the highest values for matrix production, greatest changes in metabolite consumption or production, and highest histological scores, indicating that the network was able to recognize patterns amongst diverse measurement outcomes. These results demonstrated the utility of artificial neural network tools for recognizing relationships in systems with competing parameters, toward the goal of optimizing and accelerating the design of biomaterial scaffolds for articular cartilage tissue engineering.

Neural network evidence for the coupling of presaccadic visual remapping to predictive eye position updating

As we look around a scene, we perceive it as continuous and stable even though each saccadic eye movement changes the visual input to the retinas. How the brain achieves this perceptual stabilization is unknown, but a major hypothesis is that it relies on presaccadic remapping, a process in which neurons shift their visual sensitivity to a new location in the scene just before each saccade. This hypothesis is difficult to test in vivo because complete, selective inactivation of remapping is currently intractable. We tested it in silico with a hierarchical, sheet-based neural network model of the visual and oculomotor system. The model generated saccadic commands to move a video camera abruptly. Visual input from the camera and internal copies of the saccadic movement commands, or corollary discharge, converged at a map-level simulation of the frontal eye field (FEF), a primate brain area known to receive such inputs. FEF output was combined with eye position signals to yield a suitable coordinate frame for guiding arm movements of a robot. Our operational definition of perceptual stability was "useful stability,” quantified as continuously accurate pointing to a visual object despite camera saccades. During training, the emergence of useful stability was correlated tightly with the emergence of presaccadic remapping in the FEF. Remapping depended on corollary discharge but its timing was synchronized to the updating of eye position. When coupled to predictive eye position signals, remapping served to stabilize the target representation for continuously accurate pointing. Graded inactivations of pathways in the model replicated, and helped to interpret, previous in vivo experiments. The results support the hypothesis that visual stability requires presaccadic remapping, provide explanations for the function and timing of remapping, and offer testable hypotheses for in vivo studies. We conclude that remapping allows for seamless coordinate frame transformations and quick actions despite visual afferent lags. With visual remapping in place for behavior, it may be exploited for perceptual continuity.

Multicomponent gas-mixture measurements using an array of gas sensors and an artificial neural-network

An Electronic Nose is being jointly developed between the University of Greenwich and the Institute of Intelligent Machines to detect the gases given off from an oil filled transformer when it begins to break down. The gas sensors being used are very simple, consisting of a layer of Tin Oxide (SnO2) which is heated to approximately 640 K and the conductivity varies with the gas concentrations. Some of the shortcomings introduced by the commercial gas sensors available are being overcome by the use of an integrated array of gas sensors and the use of artificial neural networks which can be 'taught' to recognize when the gas contains several components. At present simulated results have achieved up to a 94% success rate of recognizing two component gases and future work will investigate alternative neural network configurations to maintain this success rate with practical measurements.