EVOLVABLE BINARY ARTIFICIAL NEURAL NETWORK FOR DATA CLASSIFICATION
Janusz A. Starzyk, Jing Pang · 2000
This paper describes a new evolvable hardware organization and its learning algorithm to generate binary logic artificial neural networks based on mutual information and statistical analysis. First, thresholds to convert analog signals of the training data to digital signals are established. In order to extract feature function for multidimensional data classification, conditional entropy is calculated to obtain maximum information in each subspace. Next, dynamic shrinking and expansion rules are developed to build the feed forward neural networks. At last, hardware mapping of learning patterns and on-board testing are implemented on Xilinx FPGA board.