{"product_id":"applied-deep-learning-with-tensorflow-2-9781484280195","title":"Applied Deep Learning with TensorFlow 2","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003e\u003cp\u003eUnderstand how neural networks work and learn how to implement them using TensorFlow 2.0 and Keras. This new edition focuses on the fundamental concepts and at the same time on practical aspects of implementing neural networks and deep learning for your research projects.\u003cbr\u003e\u003c\/p\u003e\u003cp\u003eThis book is designed so that you can focus on the parts you are interested in. You will explore topics as regularization, optimizers, optimization, metric analysis, and hyper-parameter tuning. In addition, you will learn the fundamentals ideas behind autoencoders and generative adversarial networks.\u003c\/p\u003e\u003cp\u003eAll the code presented in the book will be available in the form of Jupyter notebooks which would allow you to try out all examples and extend them in interesting ways. A companion online book is available with the complete code for all examples discussed in the book and additional material more related to TensorFlow and Keras. All the code will be available in Jupyter notebook format and can be opened \u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003eChapter 1 :  Optimization and neural networks\u003cbr\u003eSubtopics:\tHow to read the book\tIntroduction to the book\u003cbr\u003eChapter 2:  Hands-on with One Single NeuronSubtopics:\tOverview of optimization\tA definition of learning\tConstrained vs. unconstrained optimization\tAbsolute and local minima\tOptimization algorithms with focus on Gradient Descent\tVariations of Gradient Descent (mini-batch and stochastic)\tHow to choose the right mini-batch size\u003cbr\u003eChapter 3: Feed Forward Neural NetworksSubtopics:\tA short introduction to matrix algebra\tActivation functions (identity, sigmoid, tanh, swish, etc.)\tImplementation of one neuron in Keras\tLinear regression with one neuron\tLogistic regression with one neuron\u003cbr\u003eChapter 4: RegularizationSubtopics:\tMatrix formalism\tSoftmax activation function\tOverfitting and bias-variance discussion\tHow to implement a fully conneted network with Keras\tMulti-class classification with the Zalando dataset in Keras\tGradient descent variation in practice with a real dataset\tWeight initialization\tHow to compare the complexity of neural networks\tHow to estimate memory used by neural networks in Keras \u003cbr\u003eChapter 5: Advanced OptimizersSubtopics:\tAn introduction to regularization\tl_p norm\tl_2 regularization\tWeight decay when using regularization\tDropout\tEarly Stopping\u003cbr\u003e\u003cbr\u003eChapter 6Chapter Title: Hyper-Parameter tuningSubtopics:\tExponentially weighted averages\tMomentum\tRMSProp\tAdam\tComparison of optimizers\u003cbr\u003eChapter 7Chapter Title: Convolutional Neural NetworksSubtopics:\tIntroduction to Hyper-parameter tuning\tBlack box optimization\tGrid Search\tRandom Search\tCoarse to fine optimization\tSampling on logarithmic scale\tBayesian optimisation\u003cbr\u003eChapter 8Chapter Title:  Brief Introduction to Recurrent Neural NetworksSubtopics:\tTheory of convolution\tPooling and padding\tBuilding blocks of a CNN \tImplementation of a CNN with Keras\tIntroduction to recurrent neural networks\tImplementation of a RNN with Keras\u003cbr\u003e\u003cbr\u003eChapter 9: AutoencodersSubtopics:\tFeed Forward Autoencoders\tLoss function in autoencoders\tReconstruction error\tApplication of autoencoders: dimensionality reduction\tApplication of autoencoders: Classification with latent features\tCurse of dimensionality\tDenoising autoencoders\tAutoencoders with CNN \u003cbr\u003eChapter 10: Metric AnalysisSubtopics: \tHuman level performance and Bayes error\tBias\tMetric analysis diagram\tTraining set overfitting\tHow to split your dataset\tUnbalanced dataset: what can happen\tK-fold cross validation\tManual metric analysis: an example\u003cbr\u003eChapter 11 Chapter Title: General Adversarial Networks (GANs)Subtopics: \tIntroduction to GANs\tThe building blocks of GANs\tAn example of implementation of GANs in Keras\u003cbr\u003eAPPENDIX 1: Introduction to KerasSubtopics:\tSequential model\tKeras Layers\tFunctional APIs\tSpecifying loss functions\tPutting all together and training a model\tCallback functions\tSave and load models\u003cbr\u003eAPPENDIX 2: Customizing KerasSubtopics:\tCustom callback functions\tCustom training loops\tCustom loss functions\u003cbr\u003eAPPENDIX 3: Symbols and Abbreviations\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e","brand":"APress","offers":[{"title":"Default Title","offer_id":53515777212759,"sku":"9781484280195","price":46.74,"currency_code":"GBP","in_stock":true}],"url":"https:\/\/bookcurl.com\/products\/applied-deep-learning-with-tensorflow-2-9781484280195","provider":"Book Curl","version":"1.0","type":"link"}