深度学习(影印版)(英文版)

尽管人们对于机器学习领域的兴趣已达到高点， 但过高的期望往往在项目没走多远之前就已经压垮了 它。机器学习——特别是深度神经网络——如何才能 在你的组织内产生真正的作用？这本《深度学习(影 印版)(英文版)》不仅能提供关于该主题最实用的信 息，也可以帮助你开始构建高效的深度学习网络。 在引入开源Deeplearning4j(DL4J)库用于开发 产品级工作流之前，作者乔希·帕特森和亚当·吉普 森介绍了深度学习——调优、并行化、向量化及建立 管道——任何库所需的基础知识。通过真实的案例， 你将学会在Spark和Hadoop上用DL4J训练深度网络架 构并运行深度学习工作流的方法和策略。

Josh Patterson目前是Skymind的现场工程副总裁。他此前曾在Cloudera担任高级解决方案架构师，在Tennessee Valley Authority担任机器学习和分布式系统工程师。

Preface 1. A Review of Machine Learning The Learning Machines How Can Machines Learn? Biological Inspiration What Is Deep Learning? Going Down the Rabbit Hole Framing the Questions The Math Behind Machine Learning: Linear Algebra Scalars Vectors Matrices Tensors Hyperplanes Relevant Mathematical Operations Converting Data Into Vectors Solving Systems of Equations The Math Behind Machine Learning: Statistics Probability Conditional Probabilities Posterior Probability Distributions Samples Versus Population Resampling Methods Selection Bias Likelihood How Does Machine Learning Work? Regression Classification Clustering Underfitting and Overfitting Optimization Convex Optimization Gradient Descent Stochastic Gradient Descent Quasi-Newton Optimization Methods Generative Versus Discriminative Models Logistic Regression The Logistic Function Understanding Logistic Regression Output Evaluating Models The Confusion Matrix Building an Understanding of Machine Learning 2. Foundations of Neural Networks and Deep Learning. Neural Networks The Biological Neuron The Perceptron Multilayer Feed-Forward Networks Training Neural Networks Backpropagation Learning