A Hierarchical Self-organizing Associative Memory for Machine Learning (2009)
Abstract. This paper proposes novel hierarchical self-organizing associative memory architecture for machine learning. This memory architecture is characterized with sparse and local...
Dale E. Nelson, Janusz A. Starzyk, Senior Member, D. David Ensley
Abstract —This paper explores the use of wavelets to improve the selection of discriminant features in the target recognition problem using High Range Resolution (HRR) radar signals in an air to...
Dale E. Nelson, Janusz A. Starzyk
Rough Set Theory (RST) is a recent development in the area of data mining and knowledge discovery. RST is an emerging Automatic Target Recognition (ATR) methodology for determining features and then...
A Novel Low-Power Logic Circuit Design Scheme (2009)
Janusz A. Starzyk, Senior Member, Haibo He
Abstract—This brief proposes a novel low-power digital logic design scheme based on the energy exchange in the switched inductor–capacitor (SLC) circuit. It presents a design paradigm which in...
Associative Learning in Hierarchical Self-Organizing Learning Arrays (2009)
Janusz A. Starzyk, Senior Member, Zhen Zhu, Student Member, Yue Li
Abstract—In this paper, we introduce feedback-based associative learning in self-organized learning arrays (SOLAR). SOLAR structures are hierarchically organized networks of sparsely connected...
Fusing Marginal Reducts for HRR Target Identification (2009)
Dale E. Nelson, Janusz A. Starzyk
Rough set theory has not been applied to automatic target recognition (ATR) problems because the problems of interest were too large. The determination of reducts (classifiers) was a problem whose...
Sparse Coding in Sparse Winner Networks (2009)
Janusz A. Starzyk, Yinyin Liu, David Vogel
Abstract. This paper investigates a mechanism for reliable generation of sparse code in a sparsely connected, hierarchical, learning memory. Activity reduction is accomplished with local competitions...
Optimized Approximation Algorithm in Neural Networks Without Overfitting (2009)
Yinyin Liu, Janusz A. Starzyk, Senior Member, Zhen Zhu
Abstract—In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approximation...
Iterated wavelet transformation and signal discrimination for HRR radar target recognition (2009)
Dale E. Nelson, Senior Member, Janusz A. Starzyk, Senior Member, D. David Ensley
Abstract—This paper explores the use of wavelets to improve the selection of discriminant features in the target recognition problem using high range resolution (HRR) radar signals in an air to air...
Dynamic Probability Estimator for Machine Learning (2009)
Janusz A. Starzyk, Senior Member, Feng Wang
Abstract—An efficient algorithm for dynamic estimation of probabilities without division on unlimited number of input data is presented. The method estimates probabilities of the sampled data from...
Anticipation-Based Temporal Sequences Learning in Hierarchical Structure (2009)
Janusz A. Starzyk, Senior Member, Haibo He
Abstract—Temporal sequence learning is one of the most critical components for human intelligence. In this paper, a novel hierarchical structure for complex temporal sequence learning is proposed....
Haibo He, Student Member, Janusz A. Starzyk, Senior Member
Abstract—This paper proposed a novel approach for the Power Quality (PQ) disturbances classification based on the wavelet transform and self organizing learning array (SOLAR) system. Wavelet...
Motivation in Embodied Intelligence 6 (2009)
Before artificial intelligence set its mind on developing abstract intelligent agents which can think, Alan Turing suggested training embodied machines equipped with sensors and actuators to...
Neural Network with Memory and Cognitive Functions (2008)
Janusz A. Starzyk, Yue Li, David D. Vogel
Abstract. This paper provides an analysis of a new class of distributed memories known as R-nets. These networks are similar to Hebbian networks, but are relatively sparsly connected. R-nets use...
Online Dynamic Value System for Machine Learning (2008)
Abstract. A novel online dynamic value system for machine learning is proposed in this paper. The proposed system has a dual network structure: data processing network (DPN) and information...
Hybrid Pipeline Structure for Self-Organizing Learning Array (2008)
Janusz A. Starzyk, Mingwei Ding, Yinyin Liu
Abstract. In recent years, many efforts have been put in applying the concept of reconfigurable computing to neural networks. In our previous pursuits, an innovative self-organizing learning array...
Associative Learning in Hierarchical Self Organizing Learning Arrays (2008)
Janusz A. Starzyk, Zhen Zhu, Yue Li
Abstract. In this paper we introduce feedback based associative learning in self-organized learning arrays (SOLAR). SOLAR structures are hierarchically organized and have the ability to classify...
Self-organizing learning array (2005)
Janusz A. Starzyk, Senior Member, Zhen Zhu, Tsun-ho Liu
Abstract—A new machine learning concept—self-organizing learning array (SOLAR)—is presented. It is a sparsely connected, information theory-based learning machine, with a multilayer structure....
A Mathematical Foundation for Improved Reduct Generation in Information Systems (2000)
Janusz A. Starzyk, Senior Member, Dale E. Nelson, Kirk Sturtz
Abstract — When data sets are analyzed, statistical pattern recognition is often used to find the information hidden in the data. Another approach to information discovery is data mining. Data...