Econets: Neural networks that learn in an environment

TLDR

Ecological networks learn in an environment, where the environment—not the researcher—determines learning conditions such as input patterns and teaching signals. The study explores two hypotheses: that predicting sensory consequences of an organism’s actions is fundamental for building environmental maps, and that such prediction biases learning toward goal attainment. Simulation data support both hypotheses.

Abstract

Ecological networks are networks that learn in an environment. It is the environment, and not the researcher, that determines the conditions in which learning takes place such as which input patterns are seen, what the teaching input is, etc. Furthermore, input patterns at time N+1 are often a function of the output of the network at time N. Two hypotheses are explored with reference to ecological networks. One is that predicting the sensory consequences (input) for an organism of the organism's actions (output) on the environment is one of the basic tasks of this type of network—basic for constructing an environmental map or world model. The other is that learning to predict the sensory consequences of the organism's actions favourably predisposes the organism to learn to attain goals with those actions. Some data from simulations that support these two hypotheses are reported.