https://jamesmccaffrey.wordpress.com/2013/11/05/why-you-should-use-cross-entropy-error-instead-of-classification-error-or-mean-squared-error-for-neural-network-classifier-training/James D. McCaffrey Software Research, Development, Testing, and Education ...【阅读全文】
https://github.com/white127/insuranceQA-cnn================result==================theano and tensorflow cnn code for insuranceQAtheano code, test1 top-1 precision : 61.5% (see ./insuranceQA/acc) tensorflow code, test1 top-1 precision : 62.6%the best precision in the paper is 62.8%...【阅读全文】