Neural Networks
In this work, a neural network is trained to recognize complex associations between inputs and outputs that were presented during a supervised training cycle, and these associations are incorporated into the weights of the network.
Abstract
Artificial neural networks have been proposed as a tool for machine learning (e.g., see [23, 41, 47, 52]) and many results have been obtained regarding their application to practical problems in robotics control, vision, pattern recognition, grammatical inferences and other areas (e.g., see [8, 19, 29, 61]). In these roles, a neural network is trained to recognize complex associations between inputs and outputs that were presented during a supervised training cycle. These associations are incorporated into the weights of the network, which encode ∗Supported in part by NSF grants CCR-0206795, CCR-0208749 and IIS-0346973.