[lukejduncan]

This is one of my all time favorite technical books. I wrote a review of sorts a few years back[0]. It doesn’t cover any deep learning topics, which perhaps dates it at this point, but it gives solid fundamentals on a breadth of techniques common in industry. This is always in my recommendation list for folks making the transition from more systems or product engineering to ML.

[0] https://www.linkedin.com/pulse/introduction-statistical-lear...

[lukeplato]

Noticed your comment after posting mine: https://news.ycombinator.com/item?id=24056852

I was wondering if in retrospect you would have preferred reading the Goodfellow deep learning book vs. this?

[disgruntledphd2]

I've read both, and I would strongly recommend ISL first as it's much broader and covers the basics much much better than the Goodfellow book.

[lukejduncan]

Agreed. I’ve read both and would also recommend this first. The good fellow book goes deep fast. This was my review at the time https://www.goodreads.com/review/show/2196621333

That said, if your choice is more general, statistical learning vs deep learning, I’m sure at this point you can find more approachable deep learning primers. This book just isn’t it IMHO.