Ask HN: How to get started with machine learning? • Hacker News Board

Re: Ask HN: How to get started with machine learning?

#41

Post by hnarayanan » Sat, Oct 15, 2016, 1:48 PM UTC

scottmcdot wrote: post #37

nl wrote: post #31

DON'T LEARN NEURAL NETWORKS FIRST. Instead, learn decision trees and more importantly enough statistics so you aren't dangerous. Do you know what the central limit theorem is and why it is important? Can you do 5-fold cross validation on a random forest model in your choice of tool? Fine, now you are ready to do deep learning stuff. The reason I say not to do neural networks first is because they aren't very effectiv…

Thanks. Can you recommend any statistics books to be safe?

I found this a really good book: http://www-bcf.usc.edu/~gareth/ISL/

Re: Ask HN: How to get started with machine learning?

#42

Post by AndrewKemendo » Sat, Oct 15, 2016, 1:50 PM UTC

This specific topic/question comes us frequently enough that I feel like we should either make this thread the canonical answer or have another pointer that we can generally agree upon to point people in that direction.

I think it's important for people to know where to go for good resources, but this exact question keeps coming up incessantly.

Re: Ask HN: How to get started with machine learning?

#43

Post by atemerev » Sat, Oct 15, 2016, 1:58 PM UTC

NicoJuicy wrote: post #25

I'd be more interested in real life results on a small scale first. I too felt like ML is something new to try, but the lack of real world use cases on a small scale ( not google, Microsoft, ... ) Has kept me from trying/doing. I only saw the farm with image recognition for vegetables as an example for now. Anyone has other examples?

I come from finance, so for me it is always market prediction (however, the important thing is to approach this as a learning opportunity, not as a way to make profits -- for that, there are many orthogonal technical issues to solve).

Numerous ML competitions also provide enough fun to get started.

Re: Ask HN: How to get started with machine learning?

#44

Post by atemerev » Sat, Oct 15, 2016, 2:05 PM UTC

laichzeit0 wrote: post #21

You should have the equivalent of an undergraduate degree in mathematical statistics (calculus, linear algebra, et al). It should take about 4 years of full time study to achieve that. Forget about the code part. It's the least difficult part.

It takes four years of full time study to gain universal foundations to approach many different problem types.

For special applications, it is totally OK to learn as you go.

Re: Ask HN: How to get started with machine learning?

#45

Post by slantaclaus » Sat, Oct 15, 2016, 2:05 PM UTC

Take a class on linear algebra. Learn how to use matlab or octave. Knowing these two interdependent subsets of knowledge before diving into machine learning is absolutely indispensable as far as I can tell. I would've gotten so much more out of Ng's class if I knew this stuff beforehand

Re: Ask HN: How to get started with machine learning?

#46

Post by master_yoda_1 » Sat, Oct 15, 2016, 2:10 PM UTC

How is your programming background? Do some contest on hackerrank and gauge your skill because machine leaning uses lots of algorithm from math + computer science (eg computational geometry). Machine learning is basically writing some math in code and running experiment and statistically reason about result. If you really want to do that then you need to have a background in math + statistics + software development.

Re: Ask HN: How to get started with machine learning?

#47

Post by master_yoda_1 » Sat, Oct 15, 2016, 2:15 PM UTC

scottmcdot wrote: post #37

nl wrote: post #31

DON'T LEARN NEURAL NETWORKS FIRST. Instead, learn decision trees and more importantly enough statistics so you aren't dangerous. Do you know what the central limit theorem is and why it is important? Can you do 5-fold cross validation on a random forest model in your choice of tool? Fine, now you are ready to do deep learning stuff. The reason I say not to do neural networks first is because they aren't very effectiv…

Thanks. Can you recommend any statistics books to be safe?

http://www-bcf.usc.edu/~gareth/ISL/ is not an statistics book. its a statistical machine learning book.

"All of statistics" is really a great book if you have time work through he exercise.

Re: Ask HN: How to get started with machine learning?

#48

Post by asadlionpk » Sat, Oct 15, 2016, 2:15 PM UTC

If you just want to jump right in with minimal theory and then learn as you progress. Here is how I did it: https://blog.asadmemon.com/shortest-way-to-deep-learning-41e...

Re: Ask HN: How to get started with machine learning?

#49

Post by stared » Sat, Oct 15, 2016, 2:25 PM UTC

scottmcdot wrote: post #37

nl wrote: post #31

DON'T LEARN NEURAL NETWORKS FIRST. Instead, learn decision trees and more importantly enough statistics so you aren't dangerous. Do you know what the central limit theorem is and why it is important? Can you do 5-fold cross validation on a random forest model in your choice of tool? Fine, now you are ready to do deep learning stuff. The reason I say not to do neural networks first is because they aren't very effectiv…

Thanks. Can you recommend any statistics books to be safe?

MacKay, "Information Theory, Inference, and Learning Algorithms" and taking the Bayesian Inference and Machine Learning path

http://www.inference.phy.cam.ac.uk/itila/book.html (freely accessible online)

Re: Ask HN: How to get started with machine learning?

#50

Post by hrzn » Sat, Oct 15, 2016, 2:30 PM UTC

Gain background knowledge first, it will make your life much easier. It will also make the difference between just running black box libraries and understanding what's happening. Make sure you're comfortable with linear algebra (matrix manipulation) and probability theory. You don't need advanced probability theory, but you should be comfortable with the notions of discrete and continuous random variables and probability distributions.

Khan Academy looks like a good beginning for linear algebra: https://www.khanacademy.org/math/linear-algebra

MIT 6.041SC seems like a good beginning for probability theory: https://www.youtube.com/playlist?list=PLUl4u3cNGP60A3XMwZ5se...

Then, for machine learning itself, pretty much everyone agrees that Andrew Ng's class on Coursera is a good introduction: https://www.coursera.org/learn/machine-learning

If you like books, "Pattern Recognition and Machine Learning" by Chris Bishop is an excellent reference of "traditional" machine learning (i.e., without deep learning).

"Machine Learning: a Probabilistic Perspective" book by Kevin Murphy is also an excellent (and heavy) book: https://www.cs.ubc.ca/~murphyk/MLbook/

This online book is a very good resource to gain intuitive and practical knowledge about neural networks and deep learning: http://neuralnetworksanddeeplearning.com/

Finally, I think it's very beneficial to spend time on probabilistic graphical models. Here is a good resource: https://www.coursera.org/learn/probabilistic-graphical-model...

Have fun!