Basic Neural Network on Python
danielfrg.github.io
Basic Neural Network on Python
1–10 of 29 posts
Re: Basic Neural Network on Python
#2Very good write up. If you want to trade speed and memory for accuracy, you can make a large lookup table for your sigmoidal function which should just about double the speed of it.
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.
Re: Basic Neural Network on Python
#3Both datasets you used (iris and digits) are way too simple for neural networks to shine.
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.
Re: Basic Neural Network on Python
#4Very good write up. If you want to trade speed and memory for accuracy, you can make a large lookup table for your sigmoidal function which should just about double the speed of it. 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…
Definitely a native spanish speaker here :P. Because I wrote this on an iPython notebook it takes a little bit longer to spell-check. I will try not to be so lazy next time.
Thanks for the tips.
Re: Basic Neural Network on Python
#5Very good write up. If you want to trade speed and memory for accuracy, you can make a large lookup table for your sigmoidal function which should just about double the speed of it. 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…
Definitely a native spanish speaker here :P. Because I wrote this on an iPython notebook it takes a little bit longer to spell-check. I will try not to be so lazy next time. Thanks for the tips.
The only one I caught was "state of the are" in the last sentence.
Re: Basic Neural Network on Python
#6Very good write up. If you want to trade speed and memory for accuracy, you can make a large lookup table for your sigmoidal function which should just about double the speed of it. 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…
A relatively small lookup table for the sigmoid function can also work well. Here are the various sigmoid approximations that Theano (a library used for deep learning research among other things) offers: http://deeplearning.net/software/theano/library/tensor/nnet/...
Re: Basic Neural Network on Python
#7"def function(...)"
Re: Basic Neural Network on Python
#8Good writeup. Is there a feed for that blog? I only found one for the comments.
Re: Basic Neural Network on Python
#9Good writeup. Is there a feed for that blog? I only found one for the comments.
Yes: http://danielfrg.github.io/feeds/all.atom.xml
Gonna add a direct link from the site soon.
Re: Basic Neural Network on Python
#10Both datasets you used (iris and digits) are way too simple for neural networks to shine. 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 GP…
Not for nothing but Ben did you read the article? He's not even discussing most of what you mention. He is simply taking his learning and applying it. You seem to be going off on a tangent about advanced applications where he is obviously just learning about how these things work and not trying to teach a method or suggesting that he has discovered anything significant..
To the author: I liked the article. A simple, concise read.