Behold, a thread where people who wish some machine learning-based webservice, library/framework or application existed meet people who are looking for a fun project idea to implement! Pure magic.
What are some fun project ideas in machine learning? :)
1–10 of 11 posts
Re: What are some fun project ideas in machine learning? :)
#2Animal sound detector
Speech recognition for cows,dogs,birds etc.
Moo,chirp,meow
Re: What are some fun project ideas in machine learning? :)
#3Animal sound detector Speech recognition for cows,dogs,birds etc. Moo,chirp,meow
Whoah, sounds interesting! What could it be for, any applications in mind?
Re: What are some fun project ideas in machine learning? :)
#4Animal sound detector Speech recognition for cows,dogs,birds etc. Moo,chirp,meow
Whoah, sounds interesting! What could it be for, any applications in mind?
maybe a birdwatcher app. because mostly birdwatchers do not see their targets but only hear it.
and of course a siri plugin: hey siri, what sound/song is that?
Re: What are some fun project ideas in machine learning? :)
#5I have an idea of a project involving Machine Learning, applied to the game of chess:
You would need a large database of chess games and a program that can detect some features in a position (for example: "white are a pawn up", "black pawn structure is better", "black king is not safe", etc.).
The idea would be to see if some features in a position are making one side more likely to win. For example, we might find that being a piece up makes one side more likely to win, since the largest majority of the cases when one side had a piece up, it ended up winning.
But that's not an interesting result. What I would like to see if it's possible to discover features that are good for one side, and which we didn't know about.
I didn't have time to start anything about it, though.
Re: What are some fun project ideas in machine learning? :)
#6Here are the final projects for CS 229: Machine Learning at Stanford.
http://cs229.stanford.edu/projects2012.html
Take any of these studies, and try to replicate or extend it. They're all pretty interesting and come with the advantage that you get to see how someone else approached the problem as well.
Re: What are some fun project ideas in machine learning? :)
#7Here are the final projects for CS 229: Machine Learning at Stanford. http://cs229.stanford.edu/projects2012.html Take any of these studies, and try to replicate or extend it. They're all pretty interesting and come with the advantage that you get to see how someone else approached the problem as well.
This is very helpful and what I was looking for. Thank you.
Re: What are some fun project ideas in machine learning? :)
#8I posted some a little while ago: http://blog.andrewcantino.com/blog/2012/04/22/machine-learni...
Re: What are some fun project ideas in machine learning? :)
#9I posted some a little while ago: http://blog.andrewcantino.com/blog/2012/04/22/machine-learni...
Very cool.
Just wondering out loud reg. your idea to a have a rick roll detector: How exactly would that work? A brute force approach would be to compare how similar the target video is to some sample rick roll videos, I am guessing music matching could be attempted since frame by frame duplicate detection of the video is insanely hard.
From a machine learning perspective, it gets harder because a good rick roll entices the target into clicking the link which turns out to be a false positive. On the other hand, the link could be completely normal so the features of the link itself or not necessarily useful. Hmmm...
Re: What are some fun project ideas in machine learning? :)
#10I have an idea of a project involving Machine Learning, applied to the game of chess: You would need a large database of chess games and a program that can detect some features in a position (for example: "white are a pawn up", "black pawn structure is better", "black king is not safe", etc.). The idea would be to see if some features in a position are making one side more likely to win. For example, we might find th…
Have you checked out chess problems and go problems? They're usually presented in bulk in structured data.
http://www.chessproblems.com/
I haven't look at any in a long time, but it at least should highlight some problems hard for humans, which implies something can be learned there, imho.