As an aside, and not to be too critical, because the post was great, but as (presumably) a non-native English speaker, you might do a spell-checker on your post. There are also some missing pronouns which make some sentences very Spanishy.
Thanks for the tips.
Neural networks / deep neural networks work best in domains where the underlying data has a very rich, complex, and hierarchical structure (such as computer vision and speech recognition). Currently, training these models is both computationally expensive and fickle. Most state of the art research in this area is performed on GPU's and there are many tuneable parameters.
For most typical applied machine learning problems, especially on simpler datasets that fit in RAM, variants of ensembled decision trees (such as Random Forests) to perform at least as well as neural networks with less parameter tuning and far shorter training times.
To the author: I liked the article. A simple, concise read.
This was a nice post, but it's reasonable to warn users not to overgeneralize the algorithm comparison.
(Ben I know you're aware of all this already, but I just wanted to clarify for those who aren't as on top of the research as you)
- Resilient Propagation (RPROP), it significantly speeds up training for full batch learning: http://davinci.fmph.uniba.sk/~uhliarik4/recognition/resource...
- RMSProp, introduced by Geoffrey Hinton, also speeds up training but can also be used for mini-batch learning: https://class.coursera.org/neuralnets-2012-001/lecture/67 (sign up to view the video)
Please consider more datasets when benchmarking methods:
- MNIST ( 70k 28x28 pixel images of handwritten digits ): http://yann.lecun.com/exdb/mnist/ . There are several wrappers for Python on github.
- UCI Machine Learning Repository: http://archive.ics.uci.edu/ml/datasets.html
Thanks for the suggestions.
Just for future reference I did ran the fitting a few times founding very(+-2%) similar results. Also Random Forests do an average so probably not much to improve on that particular algorithm.
Which browser are you using?
Backprop falls within the class of 'supervised learning' which can indeed be said not to be very biologically realistic. However, reinforcement learning is observed, so the overall picture is probably much more complex: e.g. associative/recurrent/etc networks with Hebb-like unsupervised learning developing neuronal group testing and selection systems that involve reinforcement learning. (see first lecture/talk in [3].)
Perhaps worth a watch is a very nice talk by Geoffrey Hinton [2], which is oft referred to on HN. (Hinton does refer to the notion of biological plausibility etc. in this talk as far as I recall, but the focus is elsewhere (developing next generation state-of-the-art (mostly unsupervised) machine learning techniques/systems.))
[1]: https://en.wikipedia.org/wiki/Hebbian_theory
[2]: https://www.youtube.com/watch?v=AyzOUbkUf3M
[3]: http://kostas.mkj.lt/almaden2006/agenda.shtml (The original summary HTML file is gone from the original source, so this is a mirror; the links to videos and slides do work, though.) The first and the second talks are somewhat relevant (particularly the first one, re: bio plausibility etc ("Nobelist Gerald Edelman, The Neurosciences Institute: From Brain Dynamics to Consciousness: A Prelude to the Future of Brain-Based Devices")), but all are great. Rather heavy, though. (Also, skip the intros.)
edit that first talk/lecture from Almaden (Edelman's) is actually a very nice exposure of the whole paradigm in which {cognitive,computational,etc} neuroscience rests; it does get hairy later on; overall, it's a great talk for the truly curious.
Gonna add a direct link from the site soon.