Back Propagation For Classification ( Research Essay )

3007 Words May 24th, 2015 13 Pages
Back Propagation for Classification (Research Essay)
Linfeng Gu

Introduction
This research essay mainly discusses back propagation used in artificial neural networks based on three research papers. From the second section, each section contains the discussion of one research paper.
In the first research paper, researchers apply feed forward neutral networks with back propagation in medical fields and present several statistical normalization methods. [4]
In the second research paper, researchers focus on a varia¬tion of the standard back propagation algorithm. Since nodes of each layer are fully connected in the standard back propagation neural networks, huge computing resour¬ces are cost to adjust weights. Therefore researchers pro¬pose an exclusive connecting network.
In the third research paper, researchers introduce an adap¬tive gain for the activation function used in back propa¬gation neural networks in order to get faster convergence and better performance in classification problems.
Statistical Normalization and Back Propaga¬tion for Classification
Background Study
In medical fields, clinical databases are recently becoming increasingly large so that more experts are needed to deal the data. Since the majority of the medical data sets are non-linear, it is difficult for people to analysis and classify a large amount of them. Therefore if there are some specific algorithms which could automatically handle numerous data, it could efficiently reduce the human…
Open Document