The author points out something about these Machine Learning contests and Machine Learning in general that I've noticed for a while - feature selection tends to dominate learning algorithm selection. It's good to see that there are modern academic methods for feature discovery that seem to be on par with (or better than) a domain expert manually selecting features.
Yes, but just as with normal feature engineering, don't make the mistake of thinking that these methods are fully automatic work by magic. There is no free lunch.
A common criticism with these methods is that they merely shift engineering from features to parameters that specify the architecture. There are many choices to be made: The exact number of layers, number of neurons per layer, the connectivity, sparsity parameters, non-linearities, sizes of receptive fields, learning rates, weight decays, pre-training schedule etc etc etc. Perhaps even worse, while you can use intuition to design features, it is not as trivial to see if you should be using a sigmoid, tanh, or rectified linear units (+associated parameters for each) in the 3rd layer of the network. And maybe even worse, these parameters can actually have quite a strong effect on the final performance.
These are still powerful models and we are learning a lot about what works and what doesn't (and I'm optimistic) but don't make the mistake of thinking they are automatic. For now, you need to know what you're doing.
Given that pharma is a massive industry and that drug discovery often costs around 1 billion dollars, the top prize of $22,000 seems awfully low. Will we start to see larger prizes, or will startups take this technology and monetize better than academia currently does?
With Geoffrey Hinton involved as a supervisor I expect they were on the bleeding edge for other reasons anyway and just decided to scoop up some extra cash as well. I've not looked closely but Kaggle does seem to be a little like 99designs though.
[+] [-] etrain|13 years ago|reply
[+] [-] karpathy|13 years ago|reply
A common criticism with these methods is that they merely shift engineering from features to parameters that specify the architecture. There are many choices to be made: The exact number of layers, number of neurons per layer, the connectivity, sparsity parameters, non-linearities, sizes of receptive fields, learning rates, weight decays, pre-training schedule etc etc etc. Perhaps even worse, while you can use intuition to design features, it is not as trivial to see if you should be using a sigmoid, tanh, or rectified linear units (+associated parameters for each) in the 3rd layer of the network. And maybe even worse, these parameters can actually have quite a strong effect on the final performance.
These are still powerful models and we are learning a lot about what works and what doesn't (and I'm optimistic) but don't make the mistake of thinking they are automatic. For now, you need to know what you're doing.
[+] [-] username3|13 years ago|reply
[+] [-] doobwa|13 years ago|reply
[+] [-] jklio|13 years ago|reply
[+] [-] joelthelion|13 years ago|reply