FacingTheSunCN的专栏

复旦大学 吴立德教授 深度学习（Deep Learning）课程（http://www.youku.com/playlist_show/id_21508721.html），老先生讲得很细致，非常推荐。 直接利用Deep Neural Networks的问题： 以前机器学习的数据量不是很大（标记数据更少），而DNN待学习的参数非常的多（Andrew Ng在Google搞的那个有1.15b

From http://deeplearning.stanford.edu/wiki/index.php/Self-Taught_Learning There are two common unsupervised feature learning settings, depending on what type of unlabeled data you have. The more ge

在分类问题中，多类问题的处理方式通常有如下两种方法： one vs. all (one vs. rest) The one-vs.-rest (or one-vs.-all, OvA or OvR) strategy involves training a single classifier per class, with the samples of that class as po