If you don't know linear algebra already, you cannot really hope to followĪnything (especially in the way the book is written). Which is a waste of useful space that could have been spent on actual explanations in otherĬhapters. At the other extreme of audience expectation, we have a review of linear algebra in the beginning, The level ofĭetail is more similar to an expanded ACM Computing Surveys article rather than a textbook in Like a prose description of a bibliography, with equations thrown in for annotation. To be have no understanding of the didactic intention of a textbook (beyond a collation or importance sampling More than half of this book reads like a bibliographic notes section of a book, and the authors seem ![]() Would also not gain much because it is too superficial, when it comes to the advanced topics (final 35% of book). It also does not provide a good overview ("big picture thinking"). I do not wish to speculate on the reason for this but it does sometimes does occur withĪ first book in an important area or when dealing with pioneer authors with a cult following.įirst of all, it is not clear who is the audience-the writing does not provide details at the level oneĮxpects from a textbook. The disconnect between the majority of cloyingly effusive reviews of this book and the reality of how it is written Reviews tend to attract aggressively negative comments of an almost personal nature. Only a few of the reviews clearly state the obvious problems of this book. I eagerly bought it based on all the positive reviews it had received.īad mistake. I am surprised by how poorly written this book is. Looks original but the binding could use some work. And in light of all the feedback regarding dubious clones being sold under the guise of the original book, I felt it best to go with a seller with whom I have a great experience with. Their offering was ~Rs 300 more than the cheapest offer from another seller but I have brought most of my electronic gadgets from these guys and they have never disappointed. Hopefully it's a feature to prevent the binding from breaking if it was too stiff but I guess that's a story that only time will tell. I, however, found that the binding the book is weak just holding it in your hands causes the hardcovers to twist the binding. It is firm and thick and not flimsy by any means. Page quality is good don't expect laminated-paper quality. Also, I found that all the pictures are color something to look out for when you're checking this book as many previous customers (not for this seller in particular) had complained that the pages were missing or entirely replaced with a duplicate of other pages. I checked the page numbers to see if any were duplicated or shuffled. A website offers supplementary material for both readers and instructors. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models.ĭeep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. ![]() It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. This book introduces a broad range of topics in deep learning. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones a graph of these hierarchies would be many layers deep. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. “Written by three experts in the field, Deep Learning is the only comprehensive book on the subject.” -Elon Musk, cochair of OpenAI cofounder and CEO of Tesla and SpaceXĭeep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. ![]() An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |