深度学习(影印版)
内容简介
[
在引入开源Deeplearning4j（DL4J）库用于开发产品级工作流之前，作者Josh Patterson和Adam Gibson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。* 深入机器学习一般概念，特别是深度学习相关概念* 理解深度网络如何从神经网络基础演化* 探索主流深度网络架构，包括Convolutional和Recurrent * 学习如何将特定的深度网络映射到具体的问题* 一般神经网络和特定深度网络架构调优基础概览* 为不同的数据类型使用DL4J的工作流工具DateVec实现向量化* 学习如何在Spark和Hadoop本地使用DL4J
]
作者简介
[
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。
Adam Gibson是Skymind的CTO。Adam曾与财富500强企业、对冲基金、公关公司和创投加速器等机构合作，创建它们的机器学习项目。他在帮助这些公司处理和阐释大规模实时数据方面颇具深厚经验。
]
目录
Preface1. A Review of Machine LearningThe Learning MachinesHow Can Machines Learn?Biological InspirationWhat Is Deep Learning?Going Down the Rabbit HoleFraming the QuestionsThe Math Behind Machine Learning： Linear AlgebraScalarsVectorsMatricesTensorsHyperplanesRelevant Mathematical OperationsConverting Data Into VectorsSolving Systems of EquationsThe Math Behind Machine Learning： StatisticsProbabilityConditional ProbabilitiesPosterior ProbabilityDistributionsSamples Versus PopulationResampling MethodsSelection BiasLikelihoodHow Does Machine Learning Work?RegressionClassificationClusteringUnderfitting and OverfittingOptimizationConvex OptimizationGradient DescentStochastic Gradient DescentQuasi-Newton Optimization MethodsGenerative Versus Discriminative ModelsLogistic RegressionThe Logistic FunctionUnderstanding Logistic Regression OutputEvaluating ModelsThe Confusion MatrixBuilding an Understanding of Machine Learning2. Foundations of Neural Networks and Deep Learning.Neural NetworksThe Biological NeuronThe PerceptronMultilayer Feed-Forward NetworksTraining Neural NetworksBackpropagation LearningActivation FunctionsLinearSigmoidTanhHard TanhSoftmaxRectified LinearLoss FunctionsLoss Function NotationLoss Functions for RegressionLoss Functions for ClassificationLoss Functions for ReconstructionHyperparametersLearning RateRegularizationMomentumSparsity3. Fundamentals of Deep Networks4. Major Architectures of Deep Networks5. Building Deep Networks6. Tuning Deep Networks7. Tuning Specific Deep Networks Architecture8. Vectorization9. Using Deep Learning and DL4J on SparkA. What Is Artificial Intelligence?B. RL4J and Reinforcement LearningC. Numbers Everyone Should KnowD. Neural Networks and Backpropagation： A Mathematical ApproachE. Using the ND4J API
封面
书名:深度学习(影印版)
作者:Josh Patterson著
页数:507页
定价:¥99.0
出版社:东南大学出版社
出版日期:2018-02-01
ISBN:9787564175160
PDF电子书大小:131MB 高清扫描完整版