{"product_id":"modern-deep-learning-design-and-application-development-9781484274125","title":"Modern Deep Learning Design and Application","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003eLearn how to harness modern deep-learning methods in many contexts. Packed with intuitive theory, practical implementation methods, and deep-learning case studies, this book reveals how to acquire the tools you need to design and implement like a deep-learning architect. It covers tools deep learning engineers can use in a wide range of fields, from biology to computer vision to business. With nine in-depth case studies, this book will ground you in creative, real-world deep learning thinking.You'll begin with a structured guide to using Keras, with helpful tips and best practices for making the most of the framework. Next, you'll learn how to train models effectively with transfer learning and self-supervised pre-training. You will then learn how to use a variety of model compressions for practical usage. Lastly, you will learn how to design successful neural network architectures and creatively reframe difficult problems into solvable ones. You'll learn notonly to understand and appl\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003eChapter 1: “A Deep Dive Into Keras”Chapter Goal: To give a structured yet deep overview of Keras and to lay the groundwork for implementations in future chapters.Number of Pages: ~30Subtopics1.\tWhy Keras? Versatility and simplicity.2.\tSteps needed to create a Keras model: define architecture, compile, fit.a.\tCompile: discuss TensorFlow optimizers, losses, and metrics.b.\tFit: discuss callbacks.3.\tSequential model + example.4.\tFunctional model + example.5.\tVisualizing Keras models.6.\tData: using NumPy arrays, Keras Image Data Generator, and TensorFlow datasets.7.\tHardware: using and accessing CPU, GPU, and TPU.\u003cbr\u003eChapter 2: Pre-training Strategies and Transfer LearningChapter Goal: To understand the importance of transfer learning and to use a variety of transfer learning methods to solve deep learning problems efficiently.Number of Pages: ~30Subtopics1.\tTransfer learning theory, practical tips and tricks.2.\tAccessing and using Keras and TensorFlow pretrained models.a.\tBonus: converting PyTorch models (PyTorch has a wider variety) into Keras models for greater access to pretrained networks.3.\tManipulating pretrained models with other network elements.4.\tLayer freezing.5.\tSelf-supervised learning methods.\u003cbr\u003eChapter 3: “The Versatility of Autoencoders”Chapter Goal: To understand the versatility of autoencoders and to be able to use them in a wide variety of problem scenarios.Number of Pages: ~30Subtopics1.\tAutoencoder theory.2.\tOne-dimensional data autoencoder implementation, tips and tricks.3.\tConvolutional autoencoder implementation, tips and tricks, special concerns.4.\tUsing autoencoders for pretraining.a.\tExample case study: TabNet.5.\tUsing autoencoders for feature reduction.6.\tVariational autoencoders for data generation.\u003cbr\u003eChapter 4: “Model Compression for Practical Deployment”Chapter Goal: To understand pruning theory, implement pruning for effective model compression, and to recognize the important role of pruning in modern deep learning research.Number of Pages: ~20Subtopics1.\tPruning theory.2.\tPruning Keras models with TensorFlow.3.\tExciting implications of pruning – the Lottery Ticket Hypothesis.a.\tExample case-study: no-training neural networks.b.\tExample case-study: extreme learning machines.\u003cbr\u003eChapter 5: “Automating Model Design with Meta-Optimization”Chapter Goal: To understand what meta-optimization is and to be able to use it to effectively automate the design of neural networks.Number of Pages: ~20Subtopics1.\tMeta-optimization theory.2.\tDemonstration of meta-optimization using HyperOpt on Keras.3.\tDemonstration of Auto-ML and Neural Architecture Search.\u003cbr\u003e\u003cbr\u003eChapter 6: “Successful Neural Network Architecture Design”Chapter Goal: To gain an understanding of principles in successful neural network architecture design through three case studies.Number of Pages: ~25Subtopics1.\tDiversity of neural network designs and the need to design specific architectures for particular problems.2.\tTheory and implementation of block\/cell\/module design and considerations.a.\tExample case study: Inception model.3.\tTheory and implementation of “Normal” and “extreme” usages of skip connections.a.\tParallel towers and cardinalityb.\tExample case study: UMAP model.4.\tNeural network scaling.a.\tExample case study: EfficientNet.\u003cbr\u003eChapter 7: “Reframing Difficult Deep Learning Problems”Chapter Goal: To explore how hard problems can be reframed to be solved by deep learning with three case studies.Number of Pages: ~30Subtopics1.\tThe diversity of problems deep learning is being used to solve.2.\tExample case study: Siamese networks – experimenting with architecture.3.\tExample case study: DeepInsight – experimenting with data representation.4.\tExample case study: Semi-supervised generative adversarial networks – experimenting with data availability.\u003cbr\u003e","brand":"APress","offers":[{"title":"Default Title","offer_id":48885827502423,"sku":"9781484274125","price":37.49,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9781484274125.jpg?v=1722537840","url":"https:\/\/bookcurl.com\/products\/modern-deep-learning-design-and-application-development-9781484274125","provider":"Book Curl","version":"1.0","type":"link"}