An Adaptive Network That Learns Sequences of Transitions
نویسنده
چکیده
We describe an adaptive network, TIN2, that learns the transition function of a sequential system from observations of its behavior. It integrates two subnets, TIN-I (Winter, Ryan and Turner, 1987) and TIN-2. TIN-2 constructs state representations from examples of system behavior, and its dynamics are the main topics of the paper. TIN-I abstracts transition functions from noisy state representations and environmental data during training, while in operation it produces sequences of transitions in response to variations in input. Dynamics of both nets are based on the Adaptive Resonance Theory of Carpenter and Grossberg (1987). We give results from an experiment in which TIN2 learned the behavior of a system that recognizes strings with an even number of l's .
منابع مشابه
Learning Aspect Graph Representations from View Sequences
In our effort to develop a modular neural system for invariant learning and recognition of 3D objects, we introduce here a new module architecture called an aspect network constructed around adaptive axo-axo-dendritic synapses. This builds upon our existing system (Seibert & Waxman, 1989) which processes 20 shapes and classifies t.hem into view categories (i.e ., aspects) invariant to illuminat...
متن کاملNetworks which learn to store variable-length sequences in a fixed set of unit activations
A method for storing sequences of varying lengths in a fixed-width vector is described. The method is implemented, in an adaptive form, in a recurrent network which learns to generate sequences. The performance of this network is compared with that of a more conventional recurrent network on the same task.
متن کاملTonal Music as a Componential Code: Learning Temporal Relationships between and within Pitch and Timing Components
QLD 4072 Australia [email protected] This study explores the extent to which a network that learns the temporal relationships within and between the component features of Western tonal music can account for music theoretic and psychological phenomena such as the tonal hierarchy and rhythmic expectancies. Predicted and generated sequences were recorded as the representation of a 153-note waltz ...
متن کاملadaptive control of two-link robot manipulator based on the feedback linearization method and the proposed neural network
This paper proposes an adaptive control method based on the feedback linearization technique and a proposed neural network, for tracking and position control of an industrial manipulator. At first, it is assumed that the dynamics of the system are known and the control signal is constructed by the feedback linearization method. Then to eliminate the effects of the uncertainties and external d...
متن کاملAdaptive Predictive Controllers Using a Growing and Pruning RBF Neural Network
An adaptive version of growing and pruning RBF neural network has been used to predict the system output and implement Linear Model-Based Predictive Controller (LMPC) and Non-linear Model-based Predictive Controller (NMPC) strategies. A radial-basis neural network with growing and pruning capabilities is introduced to carry out on-line model identification.An Unscented Kal...
متن کامل