Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Little Learner: A Straight Line to Deep Learning

mitpress.mit.edu

Post reply on HN
Print view View original

51–60 of 102 posts

Re: The Little Learner: A Straight Line to Deep Learning

#51

Post by fumeux_fume »

bzhang255 wrote: post #31
sn9 wrote: post #28

Earlier quoted context omitted.

The great thing about Scheme is that you can learn it in less than 10 minutes and focus on the ideas.

Sure - but I think that's the least important part of my comment. The preview is basically just an intro to Scheme. I would rather be able to see how well the book covers interesting ideas about deep learning. While the jury is still out, my personal skepticism is that this is a really beautiful passion project that looks great on bookshelves, but that any serious learner would be better served dedicating their time…

More than happy to leave the traditional, high quality resources available online to the serious learners

Re: The Little Learner: A Straight Line to Deep Learning

#52

Post by rychco »

SomeHacker44 wrote: post #48

I went through some of the eBook providers but none seem to be offering a PDF version. Did anyone notice if a PDF version was for sale?

I’m also interested in this. Unfortunately, the other schemer/typer books appear to be available for kindle… so that’s likely the best we’ll get

Re: The Little Learner: A Straight Line to Deep Learning

#55

Post by fithisux »

zelphirkalt wrote: post #41
bigdict wrote: post #19

No way. Does it use Scheme? EDIT: Half Life 3 confirmed: "Presents key ideas of machine learning using a small, manageable subset of the Scheme language"

Some time ago I wrote this: https://notabug.org/ZelphirKaltstahl/guile-ml -- It contains a parallelized decision tree implementation in GNU Guile, a Scheme dialect. There is also https://github.com/lloda/guile-ffi-cblas which at least gives fast matrix multiplication. Example usage I have here: https://notabug.org/ZelphirKaltstahl/guile-math-examples/src... I don't know what is in the book, but things are possible.

Love the beauty of Scheme, but lack of types (mypy Python / Java dev/ TS dev) infuses fear to me.

I think with a little of patience I can get by.

Re: The Little Learner: A Straight Line to Deep Learning

#56

Post by alostpuppy »

SomeHacker44 wrote: post #48

I went through some of the eBook providers but none seem to be offering a PDF version. Did anyone notice if a PDF version was for sale?

Just to piggy back on this. The typesetting seems off kindle and other ebook platforms. Anyone seeing this?

Re: The Little Learner: A Straight Line to Deep Learning

#57

Post by rg111 »

zelphirkalt wrote: post #36
bzhang255 wrote: post #31

Earlier quoted context omitted.

Sure - but I think that's the least important part of my comment. The preview is basically just an intro to Scheme. I would rather be able to see how well the book covers interesting ideas about deep learning. While the jury is still out, my personal skepticism is that this is a really beautiful passion project that looks great on bookshelves, but that any serious learner would be better served dedicating their time…

This is what the book has to say (part of a foreword by Peter Norvig): > Maybe, maybe not. But even if you use a machine learning toolkit like TensorFlow or PyTorch, what you will take away from this book is an appreciation for how the fundamentals work.

I think all serious researchers have implemented core Deep Learning algorithms from scratch. I know I have.

There are two books that do exactly this:

1. Deep Learning from Scratch

2. Data Science from Scratch

In these books, you implement each part of the ML/DL pipeline, from scratch, in Python.

There is also a GitHub project call Minitorch that teaches you the inner workings of a framework like PyTorch.

And then there are several other good resources for exactly this.

What he claims to have as a content is neithet new nor unique.

Re: The Little Learner: A Straight Line to Deep Learning

#58

Post by kccqzy »

dunham wrote: post #30
dark-star wrote: post #4

Wow, I would really like to get this book to complete my set of the Little Schemer, the Seasoned Schemer and the Reasoned Schemer. But 55$ is almost twice as expensive as the other books. Yes, it is bigger than those but still... Have to think about this for a while :)

The little schemer is $40 now, reasoned schemer is $30, and the little typer is $38 (about twice as thick as the other two). I had to think on the little schemer, but grabbed it because my ten year old said that the little typer was "interesting", and I thought he might learn something from it. Probably should finish working through what I have before getting another, though.

Your ten-year-old was interested in dependent types? You can turn to the back of the book and show him that truths begin with 𝚪 ⊢

Re: The Little Learner: A Straight Line to Deep Learning

#59

Post by bilqis »

fithisux wrote: post #55
zelphirkalt wrote: post #41

Earlier quoted context omitted.

Some time ago I wrote this: https://notabug.org/ZelphirKaltstahl/guile-ml -- It contains a parallelized decision tree implementation in GNU Guile, a Scheme dialect. There is also https://github.com/lloda/guile-ffi-cblas which at least gives fast matrix multiplication. Example usage I have here: https://notabug.org/ZelphirKaltstahl/guile-math-examples/src... I don't know what is in the book, but things are possible.

Love the beauty of Scheme, but lack of types (mypy Python / Java dev/ TS dev) infuses fear to me. I think with a little of patience I can get by.

You should try typed Racket!

Re: The Little Learner: A Straight Line to Deep Learning

#60

Post by rosetremiere »

rg111 wrote: post #57
zelphirkalt wrote: post #36

Earlier quoted context omitted.

This is what the book has to say (part of a foreword by Peter Norvig): > Maybe, maybe not. But even if you use a machine learning toolkit like TensorFlow or PyTorch, what you will take away from this book is an appreciation for how the fundamentals work.

I think all serious researchers have implemented core Deep Learning algorithms from scratch. I know I have. There are two books that do exactly this: 1. Deep Learning from Scratch 2. Data Science from Scratch In these books, you implement each part of the ML/DL pipeline, from scratch, in Python. There is also a GitHub project call Minitorch that teaches you the inner workings of a framework like PyTorch. And then the…

How tied are those two books to python? If very much, are there books covering the same content with a different programming language?
Post reply on HN