【深度学习书籍】Deep Learning with Python pdf _下载

书名：Deep Learning with Python: A Hands-onIntroduction
作者: Nikhil Ketkar
出版社: Apress
出版年: 2017-5-17

内容简介

Discover the practical aspects of implementingdeep-learning solutions using the rich Python ecosystem. This book bridges thegap between the academic state-of-the-art and the industrystate-of-the-practice by introducing you to deep learning frameworks such asKeras, Theano, and Caffe. The practicalities of these frameworks is oftenacquired by practitioners by reading source code, manuals, and postingquestions on community forums, which tends to be a slow and a painful process.Deep Learning with Python allows you to ramp up to such practical know-how in ashort period of time and focus more on the domain, models, and algorithms.

This book briefly covers the mathematicalprerequisites and fundamentals of deep learning, making this book a goodstarting point for software developers who want to get started in deeplearning. A brief survey of deep learning architectures is also included.

Deep Learning with Python also introduces you to keyconcepts of automatic differentiation and GPU computation which, while notcentral to deep learning, are critical when it comes to conducting large scaleexperiments.

What You Will Learn

1.Leverage deep learning frameworks in Pythonnamely, Keras, Theano, and Caffe

2.Gain the fundamentals of deep learning withmathematical prerequisites

3.Discover the practical considerations of largescale experiments

4.Take deep learning models to production
Who This Book Is For

Software developers who want to try out deeplearning as a practical solution to a particular problem. Software developersin a data science team who want to take deep learning models developed by datascientists to production.

作者简介

Nikhil S. Ketkar currently leadsthe Machine Learning Platform team at Flipkart, India’s largest e-commerce company.He received his Ph.D. from Washington State University. Following that heconducted postdoctoral research at University of North Carolina at Charlotte,which was followed by a brief stint in high frequency trading at Transmaket inChicago. More recently he led the data mining team in Guavus, a startup doingbig data analytics in the telecom domain and Indix, a startup doing datascience in the e-commerce domain. His research interests include machinelearning and graph theory.

目录
Chapter 1: An intuitive look atthe fundamentals of deep learning based on practical applications
Chapter 2: A survey of thecurrent state-of-the-art implementations of libraries, tools and packages fordeep learning and the case for the Python ecosystem
Chapter 3: A detailed look atKeras [1], which is a high level framework for deep learning suitable forbeginners to understand and experiment with deep learning
Chapter 4: A detailed look atTheano [2], which is a low level framework for implementing architectures andalgorithms in deep learning from scratch
Chapter 5: A detailed look atCaffe [3], which is highly optimized framework for implementing some of themost popular deep learning architectures (mainly computer vision)
Chapter 6: A brief introductionto GPUs and why they are a game changer for Deep Learning
Chapter 7: A brief introductionto Automatic Differentiation
Chapter 8: A brief introductionto Backpropagation and Stochastic Gradient Descent
Chapter 9: A survey of DeepLearning Architectures
Chapter 10: Advice on runninglarge scale experiments in deep learning and taking models to production
Chapter 11: Introduction toTensorflow
Chapter 12: Introduction toPyTorch
Chapter 13: RegularizationTechniques
Chapter 14: Training Deep LeaningModels