An Enhanced Weight Update Method for Simplified ARTMAP to Classify Groundwater Data

The groundwater for aquatic purposes must be assessed prior to its consumption. Huge number of conventional methods are existing for assessing the quality of groundwater. The water quality index is one of the important conventional methods to assess the groundwater quality. But the conventional methods alone are not enough to assess groundwater quality as well as classify based on its purity. In this paper, we propose an enhanced weight update method for Simplified Fuzzy Adaptive Resonance Theory model to classify the groundwater quality depending on the relative weights of the groundwater quality parameters. Finding the optimal weights is the key to achieve better accuracy of the model, most of the nonlinear models fails to exhibit good accuracy if they fail to learn the optimal weights in the learning process. The aim of the work is to find the good fit between the predicted and the actual groundwater quality grades by identifying the optimal weights of the network by the enhanced weight update method. The Simplified Fuzzy Adaptive Resonance Theory map with the enhanced weight update method performance is justified by comparing it with the Simplified Fuzzy Adaptive Resonance Theory Map. The enhanced weight update method improves the accuracy of the Simplified Fuzzy Adaptive Resonance Theory Map in classifying and predicting the groundwater quality.

Learning to Attend, Recognize, and Predict the World

This chapter begins to explain many of our most important perceptual and cognitive abilities, including how we rapidly learn to categorize and recognize so many objects and events in the world, how we remember and anticipate events that may occur in familiar situations, how we pay attention to events that particularly interest us, and how we become conscious of these events. These abilities enable us to engage in fantasy activities such as visual imagery, internalized speech, and planning. They support our ability to learn language quickly and to complete and consciously hear speech sounds in noise. The chapter begins to explain key differences between perception and recognition, and introduces Adaptive Resonance Theory, or ART, which is now the most advanced cognitive and neural theory of how our brains learn to attend, recognize, and predict objects and events in a changing world. ART cycles of resonance and reset solve the stability-plasticity dilemma so that we can learn quickly without new learning forcing catastrophic forgetting of previously learned memories. ART can learn quickly or slowly, with supervision and without it, and both many-to-one maps and one-to-many maps. It uses learned top-down expectations, attentional focusing, and mismatch-mediated hypothesis testing to do so, and is thus a self-organizing production system. ART can be derived from a simple thought experiment, and explains and predicts many psychological and neurobiological data about normal behavior. When these processes break down in specific ways, they cause symptoms of mental disorders such as schizophrenia, autism, amnesia, and Alzheimer’s disease.

Continual Competitive Memory

In this article, we propose a novel form of unsupervised learning that we call continual competitive memory (CCM) as well as a simple framework to unify related neural models that operate under the principles of competition. The resulting neural system, which takes inspiration from adaptive resonance theory, is shown to offer a rather simple yet effective approach for combating catastrophic forgetting in continual classification problems. We compare our approach to several other forms of competitive learning and find that: 1) competitive learning, in general, offers a promising pathway towards acquiring sparse representations that reduce neural cross-talk, and, 2) our proposed variant, the CCM, which is designed with task streams in mind, is needed to prevent the overriding of old information. CCM yields promising results on continual learning benchmarks including Split MNIST and Split NotMNIST.