Neural Network Programming with TensorFlow

Unleash the power of TensorFlow to train efficient neural networks

Manpreet Singh Ghotra , Rajdeep Dua 지음

Packt(GCO Science) 2017년 11월 10일 출간

작품소개

책소개

-

목차

▶TABLE of CONTENTS
1: MATHS FOR NEURAL NETWORKS
2: DEEP FEEDFORWARD NETWORKS
3: OPTIMIZATION FOR NEURAL NETWORKS
4: CONVOLUTIONAL NEURAL NETWORKS
5: RECURRENT NEURAL NETWORKS
6: GENERATIVE MODELS
7: DEEP BELIEF NETWORKING
8: AUTOENCODERS
9: DEEP LEARNING RESEARCH IN NEURAL NETWORKS
Appendix: GETTING STARTED WITH TENSORFLOW

책 속으로

▶What this book covers
？ Chapter 1, Maths for Neural Networks, covers the basics of algebra, probability, and optimization techniques for neural networks.
？ Chapter 2, Deep Feedforward Networks, explains the basics of perceptrons, neurons, and feedforward neural networks. You will also learn about various learning techniques and mainly the core learning algorithm called backpropagation.
？ Chapter 3, Optimization for Neural Networks, covers optimization techniques that are fundamental to neural network learning.
？ Chapter 4, Convolutional Neural Networks, discusses the CNN algorithm in detail. CNNs and their application to different data types will also be covered.
？ Chapter 5, Recurrent Neural Networks, covers the RNN algorithm in detail. RNNs and their application to different data types are covered as well.
？ Chapter 6, Generative Models, explains the basics of generative models and the different approaches to generative models.
？ Chapter 7, Deep Belief Networking, covers the basics of deep belief networks, how they differ from the traditional neural networks, and their implementation.
？ Chapter 8, Autoencoders, provides an introduction to autoencoders, which have recently come to the forefront of generative modeling.
Chapter 9, Deep Learning Research and Summary, discusses the current and future research details on deep learning. It also points the readers to papers for reference reading.
？ Appendix, Getting Started with TensorFlow, discusses environment setup of TensorFlow, comparison of TensorFlow with NumPy, and the concept if Auto differentiation

출판사 서평

▶Editorial Review
If you're aware of the buzz surrounding terms such as machine learning, artificial intelligence, or deep learning, you might know what neural networks are. Ever wondered how they help solve complex computational problems efficiently, or how to train efficient neural networks? This book will teach you both of these things, and more.

You will start by getting a quick overview of the popular TensorFlow library and see how it is used to train different neural networks. You will get a thorough understanding of the fundamentals and basic math for neural networks and why TensorFlow is a popular choice. Then, you will proceed to implement a simple feedforward neural network. Next, you will master optimization techniques and algorithms for neural networks using TensorFlow. Further, you will learn how to implement some more complex types of neural networks such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Deep Belief Networks 0;(DBNs). In the course of the book, you will be working on realworld datasets to get a hands-on understanding of neural network programming. You will also get to train generative models and will learn the applications of autoencoders.

By the end of this book, you will have a fair understanding of how to leverage the power of TensorFlow to train neural networks of varying complexities, without any hassle.

작가정보

저자(글) Manpreet Singh Ghotra

Manpreet Singh Ghotra has more than 15 years of experience in software development for both enterprise and big data software. He is currently working on developing a machine learning platform/API's using open source libraries and frameworks like TensorFlow, Keras, Apache Spark and PredictionIO at Salesforce. He has worked on various machine learning systems like sentiment analysis, spam detection, image moderation and anomaly detection. He was part of the machine learning group at one of the largest online retailers in the world, working on transit time calculations using R and Apache Mahout. With a master's and a postgraduate degree in machine learning, he has contributed to and worked for the machine learning community.

저자(글) Rajdeep Dua

Rajdeep Dua has over 18 years of experience in the cloud, big data, and machine learning space. He has worked in the advocacy team for Google's big data tools, BigQuery. He has worked on the Greenplum big data platform at VMware in the developer evangelist team. He also worked closely with a team on porting Spark to run on VMware's public and private cloud as a feature set. He has taught Spark and big data at some of the most prestigious tech schools in India--IIIT Hyderabad, ISB, IIIT Delhi, and College of Engineering, Pune.Currently, he leads the developer relations team at Salesforce India. He also works with the data pipeline team at Salesforce, which uses Hadoop and Spark to expose big data processing tools for developers.He has published Big Data and Spark tutorials. He has also presented BigQuery and Google App Engine at the W3C conference in Hyderabad. He led the developer relations teams at Google, VMware, and Microsoft, and he has spoken at hundreds of other conferences on the cloud. Some of the other references to his work can be seen at Your Story and on ACM digital library.His contributions to the open source community are related to Docker, Kubernetes, Android, OpenStack, and cloud foundry. You can connect with him on LinkedIn.