a novel algorithm of extended neural networks for image recognition：一种新的扩展神经网络图像识别算法.pdf

Engineering Applications of Artificial Intelligence 42 (2015) 57–66 Contents lists available at ScienceDirect Engineering Applications of Artificial Intelligence journal homepage: /locate/engappai A novel algorithm of extended neural networks for image recognition $ Kankan Dai, Jianwei Zhao, Feilong Cao n Department of Applied Mathematics, College of Sciences, China Jiliang University, Hangzhou 310018, Zhejiang Province, PR China a r t i c l e i n f o a b s t r a c t Article history: As a class of important classifiers, feedforward neural networks (FNNs) have been used considerably in the Received 31 October 2014 study of pattern recognition. Since the inputs to FNNs are usually vectors, and many data are usually Received in revised form presented in the form of matrices, the matrices have to be decomposed into vectors before FNNs are 17 March 2015 employed. A drawback to this approach is that important information regarding correlations of elements Accepted 17 March 2015 within the original matrices are lost. Unlike traditional vector input based FNNs, a new algorithm of Available online 10 April 2015 extended FNN with matrix inputs, called two-dimensional back-propagation (2D-BP), is proposed in this Keywords: paper to classify matrix data directly, which utilizes the technique of incremental gradient descent to fully Feedforward neural networks