An Improved ART1 neural network algorithm for character recognition

Abstract

Adaptive Resonance Theory, or ART, was introduced as a theory of human cognitive information processing [1]- [2]. Its inspiration is neurobiological and its component parts are intended to model a variety of hierarchical inference levels in the human brain. ARTneural network that includes ART1, ART2 and ART3 is an unsupervised learning method. The model develops a theory for neural networks for learning pattern categories stably in response to inputs. The model is intended to solve the stability-plasticity dilemma that is faced by all the dominant intelligent systems using neural network paradigms. The properties of plasticity and stability are intimately related. A characteristic of an adequate system is the ability to adaptively switch between its stable and plastic modes. It shall be capable of maintaining plasticity in order to learn about significant new events, while remaining stable in response to irrelevant or often repeated events. ARTl network model is a self-organizing architecture capable of learning recognition categories of complex binary input patterns. It is expected to be capable of distinguishing between familiar and unfamiliar events, as well as between expected and unexpected events. The advantages of using an ART1 neural network for pattern recognition are tremendous. ART1 algorithm supports on-line learning, allowing new exemplars or events to be immediately clustering. The model doesn't have to be modified to develop a new level of optimization. The architecture of ART1 network is also structured such that numerous highly connected nodes each operate in a similar manner, making these nodes ideal for a parallel implementation. As illustrated, incorporation of the ART1 network into a parallel environment can be done with relative ease, due to the inherent parallel nature of the algorithm.Abstract: The paper indicates the shortage of standard ART1 neural network, and an improved calculating method of similarity is presented. The corresponding place value of two vectors at the same time is considered in this method. The method avoids the different result of ART1 neural network because of inputting different sequence. In order to solve the pattern excursion problem of ART1 neural network, the principle of minority subordinate to majority is proposed to reduce the appeared problem. They improve the applicative effect of ART1 neural network.