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

Ask HN: Full-on machine learning for 2020, what are the best resources?

news.ycombinator.com

Post reply on HN
Print view View original

61–70 of 122 posts

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#61

Post by LeftHandPath »

bigmit37 wrote: post #56

Is C/C++ still worth learning if o want to create some models from scratch (new layers or different paradigms) I hear that C++ is a nightmare to work with and was wondering if Rust,Julia, or even Swift would be worth learning instead. I know Python but deep learning frameworks seem to be written in C++, so to come up with new layers I need to understand C++, which I was told has lot of peculiarities that takes time t…

C++ is not as tricky as people make it out to be. There is a lot of elitism among programmers, and a lot of people seem to claim it’s hard solely to make themselves look smarter for being able to write it.

If you know the basics of programming and have the persistence to. RTFM (Read The Fucking Manual), C++ will not give you any trouble. In fact, you might actually start to enjoy it more than the other languages you used in the past.

All that said, if you are focusing on machine learning rather than programming, then you should look into Python and R. A great resource is “an introduction to data science with R” by David Langer: https://m.youtube.com/watch?v=32o0DnuRjfg

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#62

Post by jamesxv7 »

vowelless wrote: post #48

A lot of good advice here. One thing I would add is replicate a couple of ML papers. It can help develop a lot of intuition about the specific area.

Actually this is a great idea. Seems I'll try this approach for 2020 Q1.

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#63

Post by jamesxv7 »

There is a question I have been asking for quite some time. It is known that Python is the language of choice when practicing ML. But, can similar results be achieved using Powershell? What makes Python superior to Powershell when making models for ML?

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#64

Post by pinouchon »

No one suggested standford cs231n: http://cs231n.github.io/. I'd recommend the winter 2016 lectures (by FeiFei Li, Karpathy and Johnson). For getting started with convnets / deeplearning, I think this is one of the best hands on ressources out there.

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#65

Post by sweeneyrod »

codingslave wrote: post #27
sweeneyrod wrote: post #25

Earlier quoted context omitted.

I definitely agree that you don't need to go deep into theory to be able to do useful things. But I think the bias-variance tradeoff is a very bad example of "useless theory". It's essentially just another name for overfitting/underfitting, which are approximately the most important ML concepts there are.

I would again argue, the natural progression for this concept would be: 1.) Trains classifier 2.) My train error was so low! Why is my validation error so high 2.) Googles -> Why is my classifier training error lower than my validation error 3.) Learns about overfitting 4.) learns about bias variance Its always a natural progression. Reading about this stuff without encountering it means it usually doesnt stick, and…

If you already have concepts of training and validation error then you're already there. The risk is not realising you can't test on your training data, or more subtly that you can't tune hyperparameters on your test data.

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#66

Post by tehsauce »

bigmit37 wrote: post #56

Is C/C++ still worth learning if o want to create some models from scratch (new layers or different paradigms) I hear that C++ is a nightmare to work with and was wondering if Rust,Julia, or even Swift would be worth learning instead. I know Python but deep learning frameworks seem to be written in C++, so to come up with new layers I need to understand C++, which I was told has lot of peculiarities that takes time t…

You can actually implement most new layers or experimental ideas using frameworks like pytorch or tensorflow. They support fairly low-level primitives which are much more flexible than keras or pytorch sequential models. That said C/C++ is still very useful for implementing high performance systems.

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#67

Post by SaxonRobber »

bigmit37 wrote: post #56

Is C/C++ still worth learning if o want to create some models from scratch (new layers or different paradigms) I hear that C++ is a nightmare to work with and was wondering if Rust,Julia, or even Swift would be worth learning instead. I know Python but deep learning frameworks seem to be written in C++, so to come up with new layers I need to understand C++, which I was told has lot of peculiarities that takes time t…

No point unless you have an interest in numerical linear algebra. The people who write the foundational Fortran/C/C++ libraries are experts in numerical analysis which is another rabbit hole.

If you want to write your own for fun, then there are some great algebra libraries in C++ you can use or you can use bindings for PyTorch or TF.

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#68

Post by SaxonRobber »

thosakwe wrote: post #31

Does anybody have resources on the math behind ML? I hit a dead end using Python frameworks because it was a black box, and I simply lacked the underlying knowledge.

100-page ML book for a brisk tour Deep Learning (Goodfellow) Introduction to Statistical Learning

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#69

Post by codingslave »

sweeneyrod wrote: post #65
codingslave wrote: post #27

Earlier quoted context omitted.

I would again argue, the natural progression for this concept would be: 1.) Trains classifier 2.) My train error was so low! Why is my validation error so high 2.) Googles -> Why is my classifier training error lower than my validation error 3.) Learns about overfitting 4.) learns about bias variance Its always a natural progression. Reading about this stuff without encountering it means it usually doesnt stick, and…

If you already have concepts of training and validation error then you're already there. The risk is not realising you can't test on your training data, or more subtly that you can't tune hyperparameters on your test data.

True, but I guess it depends on the person. Was just trying to give HN a view of how I write code. I've found it to be faster, but I go in knowing I will be doing a ton of googling.

Re: Ask HN: Full-on machine learning for 2020, what are the best resources?

#70

Post by mlboss »

jamesxv7 wrote: post #63

There is a question I have been asking for quite some time. It is known that Python is the language of choice when practicing ML. But, can similar results be achieved using Powershell? What makes Python superior to Powershell when making models for ML?

Libraries
Post reply on HN