How to get into Machine Learning?

I'm doing pretty good with Tensorflow. I can think of some pretty sweet IM ideas for ML so I'm heading towards that. The maths are annoying but not impossible.
 
There is a person on Youtube who goes by the username Sentdex, he makes a lot of videos on python and actually has a series about machine learning. youtube(dot com)/watch?v=OGxgnH8y2NM&list=PLQVvvaa0QuDfKTOs3Keq_kaG2P55YRn5v. I found it to be really awesome. Hope it helps you out.

oseart

Looking forward to devouring this channel. Thank you!
 
check out dvlpr on youtube, watch his instagram bot videos
 
The guy on YT is just amazing. He has also other playlists about machine learning. Really awesome, thanks a lot for this info.

Actually I can't PM you. Profile isn't old enough. PM me?

Hi Chris, ah okay. Then I will sent you a PM. Can you get PM´s? I am not sure but I think. I hope, so we can get in contact. Let me know if you did not get anything.
 
Came close of winning a Kaggle competition.(Bike Share Demand)
Unfortunately finished 31st out of 3500+ people :P :P
 
Really good video course that was posted here by yt user sentdex.
After a lot of replays and side learning, I've made it to video 14.
 
I love the insights everyone has here! I'd go into deep learning from the start btw -- look into google TensorFlow and run it locally or on the cloud on AWS. The training sets are all vectorized so it makes it where it's as close to the IBM Watson stuff as possible. There is also a course on artificial intelligence/Machine Learning in finance on Coursera which gets into the very nitty gritty details of every main algo you should learn and then it gets into the immediate application versus only focusing on the conceptual.

If I were you, I'd go on Edx.org, Coursera.org and grab the book Machine Learning in a Nutshell from safaribooksonline or download it on the torrents or other download sites. PM me if anyone has any questions on this area. We've been working on using AI in regard to digital marketing lately because I moved away from this sector and got into using deep learning on areas such as genomics, proteomics, neuroprosthetics and neurotech as well as many other areas at the cutting and bleeding edge.

Is anyone working on any deep learning or even machine learning apps for the digital marketing sector? DM is very very untapped.
 
Also about training time: You will want a good NVIDIA GPU. I bought a TItan X Pascal just for ML. You don't NEED a TItan X but you should have at least a GTX 1080. 1060 or 1070 will work but will take more time to train. I'm adding a second GPU soon. They don't have to be the same model if you want to have more than one and SLI is not required. They do have to be NVIDIA to use CUDA. That or you could use Amazon GPU compute clusters and just pay a few dollars each time you want to train (Don't forget to destroy your instances/cluster when you're done!).

More on the maths: You can get by without the maths for a while just using the libraries BUT until you learn the underlying algorithms (Which has maths involved) you won't be able to tweak the algorithms or even make your own variations of them. This can sometimes mean the difference between 95% accuracy and 98% accuracy. That may not seem like a lot but of course it is.

Also, I suggest learning: Python, Nim, MATLAB, and R.

On the plus side: If you learn these things you will be part of the elite group of people with the security clearance. These skills, IMO, are essential for the coming years. It's my opinion that people who don't learn these things will soon find themselves without a job. Maybe they'll get paid some standard income but the ML coders will have a spacial place in society.

The aspects of learning Python, Nim, MATLAB and R are essential. As for the math and the underlying algorithms -- KhanAcademy is the way to go! Start on the low-end to get back into the swing of things such as with Algebra but move rapidly up the ranks into multivariable and integral calculus. You may need to also get back into probability theorems as well since many areas of advanced algorithm design is based upon probabilistic algos. You can go to town learning about the underlying data structures by knowing the math. I love your insight on how you must know math in order to create new algorithms, edit and optimize the algos. You may also want to get into deep learning with TensorFlow as well as IBM Watson's platform later on and play around after you've mastered the basics. Awesome post, @The Doctor
 
Back
Top