Enhancing incremental learning in MLP networks using ensemble encoding of network inputs

Abstract

Local learning techniques associated with Multi-layer Perceptron (MLP) networks typically employ receptive fields as an integral part of the network. However, data representation schemes that employ multiple, ouerlapping receptive fields to preprocess network inputs can be another source of local learning in MLP networks. Earlier work has shown that ensemble encoding, a distributed data representation scheme, promotes local learning and can accelerate learning in MLP networks. In this paper we demonstrate that networks using ensemble encoding display an enhanced capacity for incremental learning.