What kind of knowledge should you have before getting into this book? I've been meaning to try to learn ML and have been looking at some university courses that have all the material available.
Python.
Deep Learning with PyTorch
11–20 of 40 posts
Re: Deep Learning with PyTorch
#12For those in the ML area, what are people’s opinions on PyTorch and its use in comparison to its competition? I don’t have any experience with PyTorch or ML tech besides having to package and provide PyTorch containers for our university’s HPC cluster and running the helloworld.py against it for validation.
Re: Deep Learning with PyTorch
#13What kind of knowledge should you have before getting into this book? I've been meaning to try to learn ML and have been looking at some university courses that have all the material available.
Goodfellow’s book on deep learning[0] is a good starter - the first chapters give a solid overview of ML theory as well. Elements of Statistical Learning is another. [0] http://www.deeplearningbook.org/
Thank you. The course I looked at, and tried a little, heavily referenced that book.
Re: Deep Learning with PyTorch
#14For those in the ML area, what are people’s opinions on PyTorch and its use in comparison to its competition? I don’t have any experience with PyTorch or ML tech besides having to package and provide PyTorch containers for our university’s HPC cluster and running the helloworld.py against it for validation.
I don't have experience with PyTorch myself, but I know that Andrej Karpathy was famously happy switching to it[1].
[1]: https://twitter.com/karpathy/status/868178954032513024?lang=...
Re: Deep Learning with PyTorch
#15What kind of knowledge should you have before getting into this book? I've been meaning to try to learn ML and have been looking at some university courses that have all the material available.
Python.
Pretty much (co-author here). You can approach the book as a developer with little or no background in ML.
The purpose is exactly to get developers up to speed so that they can start perusing the already excellent online docs.
Hope you like it :-)
Re: Deep Learning with PyTorch
#16What kind of knowledge should you have before getting into this book? I've been meaning to try to learn ML and have been looking at some university courses that have all the material available.
Goodfellow’s book on deep learning[0] is a good starter - the first chapters give a solid overview of ML theory as well. Elements of Statistical Learning is another. [0] http://www.deeplearningbook.org/
I don’t think it is a good book. From a didactic point of view, I actually found it one of the worst resources out there. The math intro at the beginning is too superficial - either you know it and skip the chapter, or you need another resource to learn. The rest of the first part is okay, but parts 2 and 3 are really not very helpful to someone who doesn’t already understand it.
I strongly recommend fast.ai instead. Although often looked at as the resource for people who can’t deal with the math, I actually found it to be extremely good at explaining the math. Compare, for example, the deep learning book’s explanations on various gradient descent methods with Jemery Howard’s explanation - in the book it looks very complex, whereas in the course it’s actually really intuitive. And Jeremy doesn’t gloss over things, he actually implements the various gradient descent methods in Excel (!).
Re: Deep Learning with PyTorch
#17For those in the ML area, what are people’s opinions on PyTorch and its use in comparison to its competition? I don’t have any experience with PyTorch or ML tech besides having to package and provide PyTorch containers for our university’s HPC cluster and running the helloworld.py against it for validation.
I found it much easier to set up to run on GPU than Keras.
Re: Deep Learning with PyTorch
#18For those in the ML area, what are people’s opinions on PyTorch and its use in comparison to its competition? I don’t have any experience with PyTorch or ML tech besides having to package and provide PyTorch containers for our university’s HPC cluster and running the helloworld.py against it for validation.
Pytorch is pretty dominant in research (outside Google) but it's use in production is lagging behind, primary due to tensorflows excellent support for deployment in all kinds of environments.
I would say it's top 3, probably top 2 with potential to get better.
Re: Deep Learning with PyTorch
#19What kind of knowledge should you have before getting into this book? I've been meaning to try to learn ML and have been looking at some university courses that have all the material available.
Goodfellow’s book on deep learning[0] is a good starter - the first chapters give a solid overview of ML theory as well. Elements of Statistical Learning is another. [0] http://www.deeplearningbook.org/
God no!
That book is only useable if you are a math PhD and want to get into ML.
Source: buddy is math PhD and worked with ML for 5-10 years now, even he has hard time understanding some chapters.
Re: Deep Learning with PyTorch
#20It's not the full book and more of a preview or as it calls it "essential excerpts". Can someone add this detail to the title?