推荐kkjkok · 2013-11
“Check out this paper:”
推荐这篇训练深度网络的实用指南,含权重初始化
Bengio 总结训练深度网络常用超参数与调试经验的实践指南
这是一篇实践指南,针对基于反向传播梯度和梯度优化的学习算法,给出最常用超参数的设置建议,并讨论在需要调节大量超参数时如何处理。全文总结了成功且高效地训练、调试大规模深层多层神经网络的实践要素,最后以深层架构训练困难的开放问题收尾。
评论者把它推荐为了解梯度下降、超参数调节、权重初始化等深度网络训练实务的好入门材料。
“Check out this paper:”
“It provides a good overview for those that want to learn more about gradient descent, hyperparameter tuning, and other practical considerations involved with training deep architectures.”
“[4]: Practical recommendations for gradient-based training of deep architectures [LINK] [LINK]”