A book that explains the core ideas of neural networks and deep learning. Cool because:
* The book incorporates lots of running code for readers to explore and extend.
* The book's philosophy is to go deep into the core concepts of deep learning, not to superficially cover a long laundry list of ideas. This gives readers a solid foundation to build on, and makes understanding other material much easier.
* Deep learning is the most powerful approach known to many problems in image recognition, speech recognition, and natural language. The book will help lots more people get quickly up to speed.
The book will be freely available online, and a beta site is coming soon. Pre-beta mailing list here: http://eepurl.com/BYr9L
Awesome, signed up as well. Is your QC&QI book still accurate after 10 years of being in the wild? Have there been any advances that verify / invalidate the ideas you present?
The quantum computing book holds up okay, so far as I know. Of course, there's been many new developments since we wrote it, and a text written today would be somewhat different. But the core material in the field has changed only slowly, so a book can be surprisingly durable.
Python. I wanted to make the underlying ideas as transparent as possible, so I chose a language which many people will find accessible, and I've tried to use simple, easily understandable idioms. I hope it will also be easily accessible to people who use Python rarely.
Translation rights for books in human languages are a well established thing.
I wonder if there's any analogue for technical books using a particular computing language, ie the base explanatory text is kept the same (as much as possible) but the code samples are "translated" to another computer language ?
For example, if I didn't know Python, it would be great to be able to pick up a "translation" of your book with the code written in a similar language such as Ruby.
Obviously, only a subset of tech books could be treated in this fashion, but a way for authors to license their existing content for uses like this would be interesting.
The idea you describe seems like it would also work for learning new languages. If you already understood the subject matter in the book, you could pick up a copy for a different programming language and compare it to the copy in a language you know; comparing examples 1-to-1 would make it significantly easier (in my opinion) to understand the new language's syntax and style, and the applicability of specific features of the new language.
Dr. Andrew Appel (of Standard ML fame) wrote a compiler book, Modern Compiler Implementation in ML, in the way you're suggesting. After the ML version of the book was published, he went back and "translated" it to both C and Java to produce two new books.
* The book incorporates lots of running code for readers to explore and extend.
* The book's philosophy is to go deep into the core concepts of deep learning, not to superficially cover a long laundry list of ideas. This gives readers a solid foundation to build on, and makes understanding other material much easier.
* Deep learning is the most powerful approach known to many problems in image recognition, speech recognition, and natural language. The book will help lots more people get quickly up to speed.
The book will be freely available online, and a beta site is coming soon. Pre-beta mailing list here: http://eepurl.com/BYr9L