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 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 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.

Adaptive Resonance Associative Map: A Hierarchical ART System for Fast Stable Associative Learning

This paper introduces a new class of predictive ART architectures, called Adaptive Resonance Associative Map (ARAM) which performs rapid, yet stable heteroassociative learning in real time environment. ARAM can be visualized as two ART modules sharing a single recognition code layer. The unit for recruiting a recognition code is a pattern pair. Code stabilization is ensured by restricting coding to states where resonances are reached in both modules. Simulation results have shown that ARAM is capable of self-stabilizing association of arbitrary pattern pairs of arbitrary complexity appearing in arbitrary sequence by fast learning in real time environment. Due to the symmetrical network structure, associative recall can be performed in both directions.

A Spectral Network Model of Pitch Perception

A model of pitch perception, called the Spatial Pitch Network or SPINET model, is developed and analyzed. The model neurally instantiates ideas front the spectral pitch modeling literature and joins them to basic neural network signal processing designs to simulate a broader range of perceptual pitch data than previous spectral models. The components of the model arc interpreted as peripheral mechanical and neural processing stages, which arc capable of being incorporated into a larger network architecture for separating multiple sound sources in the environment. The core of the new model transforms a spectral representation of an acoustic source into a spatial distribution of pitch strengths. The SPINET model uses a weighted "harmonic sieve" whereby the strength of activation of a given pitch depends upon a weighted sum of narrow regions around the harmonics of the nominal pitch value, and higher harmonics contribute less to a pitch than lower ones. Suitably chosen harmonic weighting functions enable computer simulations of pitch perception data involving mistuned components, shifted harmonics, and various types of continuous spectra including rippled noise. It is shown how the weighting functions produce the dominance region, how they lead to octave shifts of pitch in response to ambiguous stimuli, and how they lead to a pitch region in response to the octave-spaced Shepard tone complexes and Deutsch tritones without the use of attentional mechanisms to limit pitch choices. An on-center off-surround network in the model helps to produce noise suppression, partial masking and edge pitch. Finally, it is shown how peripheral filtering and short term energy measurements produce a model pitch estimate that is sensitive to certain component phase relationships.

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.