Hacker News new | past | comments | ask | show | jobs | submit login
Ask HN: How to get some practical experience with ML?
5 points by colobas on Feb 17, 2017 | hide | past | favorite | 5 comments
I recently did my finished a ML course at my university and I've been also reading up a lot on the subject. However, I need to materialize what I've learned into some practical work, i.e., projects. My ultimate goal would be to become a ML engineer, but I feel like even to get an internship in the area I'd already need to have some projects to show.

What do you recommend? Project-oriented books/tutorials?


One of our guys started a tutorial series on writing an AI to play the game, DOOM. It assumes very little knowledge and is a fun exercise to do when taking a break from some of the great courses posted here. It's no replacement for the excellent course work, but it is fun.: https://www.codelitt.com/blog/doom-ai/

My favourite course for grasping the foundations of the concepts was Andrew NG's course (although it seems like you're beyond this now): https://www.coursera.org/learn/machine-learning

I think the best way to learn, is to build things though. Have you checked out the Kaggle challenges? https://www.kaggle.com/ Those will give you great practical skills.

Thanks for the insight!

Have a look at: http://www.cs.cmu.edu/~10701/projects.html for project ideas. Project A1, A2, B etc listed on the page. You can then apply the toolkit you used in the ML course and solve these and make a portfolio of your ML projects.

Kaggle could be another option.

Else a well defined problem that you may want to solve in a domain: example graphics: See some papers here: http://www.cs.ubc.ca/~van/research/machlearn.html which you could again solve in software.

thanks a lot for the tip!

*I recently finished.

Sorry for the typo.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact