GPU-Accelerated Deep Learning Library in Python
1–10 of 51 posts
Re: GPU-Accelerated Deep Learning Library in Python
#2Serious question to those with experience in the area: is the term "Deep learning" more than a buzzword?
Re: GPU-Accelerated Deep Learning Library in Python
#3Serious question to those with experience in the area: is the term "Deep learning" more than a buzzword?
It is not a buzzword, as it describes a very specific concept: learning based on a neural network with multiple (say >= 3) hidden layers.
It is not a new idea, but it has been viable only since the last few years thanks to both computational power advances (huge clusters, GPUs, big data), and algorithmic breakthroughs (sampling algorithms, stochastic optimization, contrastive divergence, ...).
Re: GPU-Accelerated Deep Learning Library in Python
#4Looks a lot like Theano [http://deeplearning.net/software/theano/index.html]
Re: GPU-Accelerated Deep Learning Library in Python
#5Serious question to those with experience in the area: is the term "Deep learning" more than a buzzword?
It is not a buzzword, as it describes a very specific concept: learning based on a neural network with multiple (say >= 3) hidden layers. It is not a new idea, but it has been viable only since the last few years thanks to both computational power advances (huge clusters, GPUs, big data), and algorithmic breakthroughs (sampling algorithms, stochastic optimization, contrastive divergence, ...).
Of course, it's also a buzzword.
Re: GPU-Accelerated Deep Learning Library in Python
#6Looks a lot like Theano [ http://deeplearning.net/software/theano/index.html ]
Theano is for compiling mathematical expressions to CUDA, it doesn't implement any deep learning itself. If anything this may be comparable to pylearn2.
Re: GPU-Accelerated Deep Learning Library in Python
#7Awesome! I'll be testing this one out when I get some free time.
Re: GPU-Accelerated Deep Learning Library in Python
#8Needs cool demos of practical applications.
Re: GPU-Accelerated Deep Learning Library in Python
#9Earlier quoted context omitted.
It is not a buzzword, as it describes a very specific concept: learning based on a neural network with multiple (say >= 3) hidden layers. It is not a new idea, but it has been viable only since the last few years thanks to both computational power advances (huge clusters, GPUs, big data), and algorithmic breakthroughs (sampling algorithms, stochastic optimization, contrastive divergence, ...).
Of course, it's also a buzzword.
Yes, often in research when there is a hot topic like this everybody tries to jump on the bandwagon, and now the term is so widely spread that attaching "deep learning" to anything makes it sound cool.
What I meant is that at least this has some specificity, in contrast with terms like "web scale", "big data", "machine learning", "2.0", that are so broad that can be attached to anything.
Re: GPU-Accelerated Deep Learning Library in Python
#10This is very interesting especially for those users more interested in running deep neural nets than programming deep neural nets. I was initially disinterested because it is missing several important features (at the moment) such as auto encoders and convolutional neural nets. A quick peek inside the example folder revealed the fact that you can specify what you want computed using YAML instead of specifying how to compute it in code means that as long as you're using something Hebel does implement you can quickly experiment with structure and parameters without worrying about programming errors. Very useful for a researcher more interested in playing with the structure of a deep neural net.
It also serializes the model and results to disk by default. This is great for loading up the model later on another, possibly less performant, machine and performing your classification / etc...
Of course PyLearn2 covers this feature set and more, but isn't as easy to get started with.
I'll make an effort to use this when I can, unfortunately my two current projects involve a convolutional neural net and an auto encoder. :(
TL; DR: Specifying structure using YAML instead of coding neural net. Working at a higher level than other libs such as Theano.