Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ersatz - Deep neural networks in the cloud

ersatz1.com

Post reply on HN
Print view View original

1–10 of 35 posts

Re: Ersatz - Deep neural networks in the cloud

#2

Post by RyanZAG »

Little bit confusing on what this actually is. Is this

1) Cloud GPU computation where you upload some special model code that is run on the neural network? ie. your own code

2) Upload data and run some pre-specified models on it, such as in the example you have a '-d model=spanish_speech_recognizer' - in which case the offering is all about how many and how good your pre-defined models are.

The two different use cases are for completely different target audiences.

Re: Ersatz - Deep neural networks in the cloud

#3

Post by fiatmoney »

RyanZAG wrote: post #2

Little bit confusing on what this actually is. Is this 1) Cloud GPU computation where you upload some special model code that is run on the neural network? ie. your own code 2) Upload data and run some pre-specified models on it, such as in the example you have a '-d model=spanish_speech_recognizer' - in which case the offering is all about how many and how good your pre-defined models are. The two different use case…

Looks like you spec some parts of the node layout & maybe types, and it fits that spec against your data. So no support for fully custom layouts / fitting methods, but you can parameterize with for instance more or less layers or number of hidden units.

Parameterizing & fitting these networks (both in having a good underlying representation, and deciding which actual parameterization to use) gets tricky & requires some domain knowledge when you start doing things like conditional or continuous RBMs.

Re: Ersatz - Deep neural networks in the cloud

#4

Post by dave_sullivan »

RyanZAG wrote: post #2

Little bit confusing on what this actually is. Is this 1) Cloud GPU computation where you upload some special model code that is run on the neural network? ie. your own code 2) Upload data and run some pre-specified models on it, such as in the example you have a '-d model=spanish_speech_recognizer' - in which case the offering is all about how many and how good your pre-defined models are. The two different use case…

Sure, I see the confusion.

So basically, you bring the data, pick the neural network architecture you want to use, and set its parameters. The model trains on the data you've given it using a GPU cluster (which still takes a while)

'spanish_speech_recognizer' is the name of the model you just trained, where 'MRNN' is the actual architecture (a multiplicative recurrent neural network as described in http://www.cs.toronto.edu/~ilya/pubs/2011/LANG-RNN.pdf) used in the example.

So the models themselves aren't pre-defined, but the architectures you can use are. You can play with a lot of different parameters (if you want), but you don't have to worry about optimizing the code for GPU or making sure your implementation of the algo itself is correct. At least that's the idea.

Re: Ersatz - Deep neural networks in the cloud

#5

Post by snippyhollow »

dave_sullivan wrote: post #4
RyanZAG wrote: post #2

Little bit confusing on what this actually is. Is this 1) Cloud GPU computation where you upload some special model code that is run on the neural network? ie. your own code 2) Upload data and run some pre-specified models on it, such as in the example you have a '-d model=spanish_speech_recognizer' - in which case the offering is all about how many and how good your pre-defined models are. The two different use case…

Sure, I see the confusion. So basically, you bring the data, pick the neural network architecture you want to use, and set its parameters. The model trains on the data you've given it using a GPU cluster (which still takes a while) 'spanish_speech_recognizer' is the name of the model you just trained, where 'MRNN' is the actual architecture (a multiplicative recurrent neural network as described in http://www.cs.toro…

Just curious, are you using an existing library like Theano, Torch or some other GPU-enabled lib?

Re: Ersatz - Deep neural networks in the cloud

#8

Post by dave_sullivan »

snippyhollow wrote: post #5
dave_sullivan wrote: post #4

Earlier quoted context omitted.

Sure, I see the confusion. So basically, you bring the data, pick the neural network architecture you want to use, and set its parameters. The model trains on the data you've given it using a GPU cluster (which still takes a while) 'spanish_speech_recognizer' is the name of the model you just trained, where 'MRNN' is the actual architecture (a multiplicative recurrent neural network as described in http://www.cs.toro…

Just curious, are you using an existing library like Theano, Torch or some other GPU-enabled lib?

Theano mostly--it really is good at what it does
Post reply on HN