Learning Environmental Contexts in a Goal-Seeking Neural Network

Thomas E. Portegys

School of Information Technology, Illinois State University, Campus Box 5150, Normal, Illinois 61790, USA.

Abstract

An important function of many organisms is the ability to learn contextual information in order to increase the probability of achieving goals. For example, a cat may watch a particular mouse hole where she has experienced success in catching mice in preference to other similar holes. Or, a person will improve his chances of getting back into his house by taking his keys with him. In this paper, predisposing conditions that affect future out-comes are referred to as environmental contexts. These conditional probabilities are learned by a goal-seeking neural network. Environmental contexts are of varying complexities are generated  that contain conditional state-transition probabilities such that the probability of some transitions is affected by the completion of others.  The neural network is capable of expressing responses that allow it to navigate the environment in order to reach a goal. The goal-seeking effectiveness of the neural network in a variety of environmental complexities is measured.

Keywords

connectionism, context learning, goal-seeking-neural networks