2.8　參考文獻

[1]　周志華．(2016)．機器學習：=Machine learning: 清華大學出版社．

[2]　Mitchell, T. M., Carbonell, J. G., & Michalski, R. S. (2003). Machine Learning:McGraw-Hill.

[3]　Bishop, C. M. (2006). Pattern Recognition and Machine Learning (Information Science and Statistics): Springer-Verlag New York, Inc.

[4]　Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective: MIT Press.

[5]　Wang, Z., & Bovik, A. C. (2009). Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures. IEEE Signal Processing Magazine, 26(1), 98-117.

[6]　Akaike, H. (1992). Information Theory and an Extension of the Maximum Likelihood Principle. Inter.symp.on Information Theory, 1, 610-624.

[7]　Shore, J. E., & Johnson, R. W. (1980). Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy. Information Theory IEEE Transactions on,26(1), 26-37.

[8]　Nakama, T. (2009). Theoretical analysis of batch and on-line training for gradient descent learning in neural networks. Neurocomputing, 73(1–3), 151-159.

[9]　Li, M., Zhang, T., Chen, Y., & Smola, A. J. (2014). Efficient mini-batch training for stochastic optimization.

[10]　Bottou, L. (2010). Large-Scale Machine Learning with Stochastic Gradient Descent:Physica-Verlag HD.

[11]　Mairal, J., Bach, F., Ponce, J., & Sapiro, G. (2009). Online Learning for Matrix Factorization and Sparse Coding. Journal of Machine Learning Research, 11(1), 19-60.

[12]　Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A., Jaitly, N., . . . Sainath, T. N.(2012). Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine, 29(6), 82-97.

[13]　Wolpert, D. H., & Macready, W. G. (1997). No free lunch theorems for optimization.IEEE Transactions on Evolutionary Computation, 1(1), 67-82.

[14]　Krizhevsky, A. (2012). Convolutional Deep Belief Networks on CIFAR-10.

[15]　Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. Paper presented at the International Joint Conference on Artificial Intelligence.

[16]　Dietterich, T. G., & Bakiri, G. (1994). Solving multiclass learning problems via error-correcting output codes: AI Access Foundation.