Reflective Learning of Neural Networks
Yoshiaki Tsukamoto, Akira Namatame Nagamatsu · Industrial and Engineering Applications of Artificial Intelligence and Expert Systems · 2022
This paper introduces the notion of an adaptive neural network model with reflection. We show how reflection can implement adaptive processes, and how adaptive mechanisms are actualized using the concept of reflection. Learning mechanisms must be understood in terms of their specific adaptive functions. We introduce an adaptive function so that a neural network is able to adjust its internal structure by itself to evolving environments by modifying its adaptive function and associated learning parameters. We also investigate reflective learning among multiple neural network modules. In multiple modules setting, two types of reflection are modeled: each neural network module learns on its own by adjusting its adaptive function, while at the same time, each neural network module mutually interacts and learns as a group to obtain the coordinated adaptive function and learning parameters.