深度学习

帮助理解深度学习：http://playground.tensorflow.org/

这里先以三位大佬(Yann LeCun, Yoshua Bengio & Geoffrey Hinton)15年在《Nature》的文章简单介绍：

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

模式识别或者说机器学习最大的痛点就是处理原始数据的能力，说白了就是特征工程部分艰难，既耗时还必须需要专业经验知识指导。我们需要：1、从感受器(麦克风等)获得原始数据；2:、进行数据预处理(降噪等)；3、特征提取；4、特征选择；5、进行预测或识别

相较而言，深度学习是一种表示学习(Representation Learning)，即可以直接将原始数据喂给深度学习模型，模型会自动发掘特征表达。简单的非线性结构组合即可学得高级抽象特征表达，且如果组合足够，可以学的任何复杂函数映射（万能近似定理(Universal approximation theorem)）。所以，深度学习可以避免大量的特征工程工作，而且只用通用学习结构即可。