%0 Generic %1 bengio2012practical %A Bengio, Yoshua %D 2012 %K learning-tips neural-network %T Practical recommendations for gradient-based training of deep architectures %U http://arxiv.org/abs/1206.5533 %X Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters. This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient and gradient-based optimization. It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters. Overall, it describes elements of the practice used to successfully and efficiently train and debug large-scale and often deep multi-layer neural networks. It closes with open questions about the training difficulties observed with deeper architectures.

@misc{bengio2012practical, abstract = {Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters. This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient and gradient-based optimization. It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters. Overall, it describes elements of the practice used to successfully and efficiently train and debug large-scale and often deep multi-layer neural networks. It closes with open questions about the training difficulties observed with deeper architectures.}, added-at = {2017-03-21T22:19:54.000+0100}, author = {Bengio, Yoshua}, biburl = {https://www.bibsonomy.org/bibtex/25fc27aa506ae1285f0c3d589c37ab263/stdiff}, description = {Practical recommendations for gradient-based training of deep architectures}, interhash = {65d13266a65cf5b992883a165f673f67}, intrahash = {5fc27aa506ae1285f0c3d589c37ab263}, keywords = {learning-tips neural-network}, note = {cite arxiv:1206.5533}, timestamp = {2017-03-21T22:19:54.000+0100}, title = {Practical recommendations for gradient-based training of deep architectures}, url = {http://arxiv.org/abs/1206.5533}, year = 2012 }