What do you think?
Rate this book
Introduction to Deep Learning
A project-based guide to the basics of deep learning.
This concise, project-driven guide to deep learning takes readers through a series of program-writing tasks that introduce them to the use of deep learning in such areas of artificial intelligence as computer vision, natural-language processing, and reinforcement learning. The author, a longtime artificial intelligence researcher specializing in natural-language processing, covers feed-forward neural nets, convolutional neural nets, word embeddings, recurrent neural nets, sequence-to-sequence learning, deep reinforcement learning, unsupervised models, and other fundamental concepts and techniques. Students and practitioners learn the basics of deep learning by working through programs in Tensorflow, an open-source machine learning framework. “I find I learn computer science material best by sitting down and writing programs,” the author writes, and the book reflects this approach.
Each chapter includes a programming project, exercises, and references for further reading. An early chapter is devoted to Tensorflow and its interface with Python, the widely used programming language. Familiarity with linear algebra, multivariate calculus, and probability and statistics is required, as is a rudimentary knowledge of programming in Python. The book can be used in both undergraduate and graduate courses; practitioners will find it an essential reference.
This concise, project-driven guide to deep learning takes readers through a series of program-writing tasks that introduce them to the use of deep learning in such areas of artificial intelligence as computer vision, natural-language processing, and reinforcement learning. The author, a longtime artificial intelligence researcher specializing in natural-language processing, covers feed-forward neural nets, convolutional neural nets, word embeddings, recurrent neural nets, sequence-to-sequence learning, deep reinforcement learning, unsupervised models, and other fundamental concepts and techniques. Students and practitioners learn the basics of deep learning by working through programs in Tensorflow, an open-source machine learning framework. “I find I learn computer science material best by sitting down and writing programs,” the author writes, and the book reflects this approach.
Each chapter includes a programming project, exercises, and references for further reading. An early chapter is devoted to Tensorflow and its interface with Python, the widely used programming language. Familiarity with linear algebra, multivariate calculus, and probability and statistics is required, as is a rudimentary knowledge of programming in Python. The book can be used in both undergraduate and graduate courses; practitioners will find it an essential reference.
- GenresComputer Science
192 pages, Hardcover
Published January 29, 2019
10 people are currently reading
77 people want to read
About the author
Eugene Charniak
19 books3 followersEugene Charniak is Professor of Computer Science at Brown University. He is the author of Statistical Language Learning (MIT Press) and other books.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 4 of 4 reviews
June 17, 2019
This review is written from the perspective of an intermediate machine learning student. Specifically I have taken a year of rigorous university machine learning coursework and a semester of general AI coursework. The last month of my most recent ML course focused on deep learning, but implementation was limited to writing a FF NN with Numpy. We did not discuss or use TF, Keras, or any other deep learning libraries.
This book picked up roughly where my class left off. It follows a logical sequence of major domains in deep learning, and introduces TF from the first chapters at a level approachable to a complete novice (like me). The figures provided were largely helpful for synthesizing the ideas, and the author's own "takes" on the algorithms and how they function were often, but not always, useful.
My foremost complaints have to be about the quality of the code provided and the editing of the book overall. First, the code provided is no longer current recommended TF usage. I know this is difficult from the author's perspective. However, it took me hours of reading the TF documentation to learn just how much of the provided code, including sessions, variable scopes, etc. are staged for obsolescence. Second, the code itself is incomplete and inconsistent in places, occasionally with mismatched variables even. The worst section of the book in these regards was chapter 4 covering RNNs. The code provided is NOT sufficient to reconstruct his example, especially because he does not explicitly discuss the dimensions of the tensors involved (perhaps the most crucial of details). I will say the book improved in the remainder of the chapters in these regards and does include more complete code and discussion in the final chapters. Third, there are general typos and poorly edited sections throughout, including lines similar to "I can't remember this [easily searched] detail off the top of my head, so we will skip it," followed a few lines later by, "I actually did look it up and [this] was the answer."
In summary, it was a useful introduction to TF and many of these deep learning disciplines, but I ended up running to the official TF tutorials and Github for answers more often than I'd like. I wish the code were current and ready for TF 2.0.
This book picked up roughly where my class left off. It follows a logical sequence of major domains in deep learning, and introduces TF from the first chapters at a level approachable to a complete novice (like me). The figures provided were largely helpful for synthesizing the ideas, and the author's own "takes" on the algorithms and how they function were often, but not always, useful.
My foremost complaints have to be about the quality of the code provided and the editing of the book overall. First, the code provided is no longer current recommended TF usage. I know this is difficult from the author's perspective. However, it took me hours of reading the TF documentation to learn just how much of the provided code, including sessions, variable scopes, etc. are staged for obsolescence. Second, the code itself is incomplete and inconsistent in places, occasionally with mismatched variables even. The worst section of the book in these regards was chapter 4 covering RNNs. The code provided is NOT sufficient to reconstruct his example, especially because he does not explicitly discuss the dimensions of the tensors involved (perhaps the most crucial of details). I will say the book improved in the remainder of the chapters in these regards and does include more complete code and discussion in the final chapters. Third, there are general typos and poorly edited sections throughout, including lines similar to "I can't remember this [easily searched] detail off the top of my head, so we will skip it," followed a few lines later by, "I actually did look it up and [this] was the answer."
In summary, it was a useful introduction to TF and many of these deep learning disciplines, but I ended up running to the official TF tutorials and Github for answers more often than I'd like. I wish the code were current and ready for TF 2.0.
Read
March 9, 2020The description of the algorithms was good but I don't like code. it was not very fluent for me.
November 1, 2019
An Excellent Book to get an Introduction to Deep Learning. I took this book to help me understand about Deep Learning within A.I.
This might be a small-scaffold for my PhD thesis. I think -- if you're new to this topic, this would be a good introduction. I think, the references and citations are useful to understand researchers and scholars involved in this field.
Deus Vult,
Gottfried
This might be a small-scaffold for my PhD thesis. I think -- if you're new to this topic, this would be a good introduction. I think, the references and citations are useful to understand researchers and scholars involved in this field.
Deus Vult,
Gottfried
October 25, 2024
สำหรับ introduction ถือว่าดี และพยายามทำให้หนังสือเล่มเล็ก ๆ ครอบคลุม แต่ภาพประกอบนี่ไม่สวย ดูไม่ค่อยตั้งใจเลย
Displaying 1 - 4 of 4 reviews