41–50 of 51 posts
Serious question to those with experience in the area: is the term "Deep learning" more than a buzzword?
I would have described the library in question as a "GPU-Accelerated Neural Network library" since that is more descriptive.
Earlier quoted context omitted.
I have this same issue and am forced to run all my experiments on AWS. Once you get a workflow down it is pretty easy and the AWS resources provide an acceptable level of performance. Though I suppose if you're just toying around / exploring it can be discouraging to go through all of that and incur AWS fees.
But you must have an Nvidia card around some where to test your codes out first? It looks like the best bang for the buck is a GTX 760.
Hm. And here I was thinking I'd seen most of the accelerated deep learning implementations. Although this one seems a touch incomplete as far as features go. There are some other for those not aware: [1] [Python] pylearn2 by the Lisa Lab @ uMontreal. Probably one of the beefiest of the bunch. Has a pretty extensive feature set, but IMO isn't the simplest to use. [2] [Python] MORB by Sander Dielman. Just restricted bo…
Went to the github page, looked for unit tests, haven't found any.
Other than that, looks promising.
Earlier quoted context omitted.
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.
Hm. And here I was thinking I'd seen most of the accelerated deep learning implementations. Although this one seems a touch incomplete as far as features go. There are some other for those not aware: [1] [Python] pylearn2 by the Lisa Lab @ uMontreal. Probably one of the beefiest of the bunch. Has a pretty extensive feature set, but IMO isn't the simplest to use. [2] [Python] MORB by Sander Dielman. Just restricted bo…
There's also Ersatz ( http://www.ersatz1.com ) -- deep learning as a service, provides a web interface that allows you to train different neural net architectures and then run them via an API, the networks are GPU backed, been in beta since January. I'm the founder and at NIPS now if anyone wants to ask me about it in person.
It looks to me as though Ersatz's focus is on providing a limited range of relatively standard models, but make them highly accessible, stable, fast, and suitable for production, whereas most available frameworks like Theano, PyLearn2, etc are more geared to the tinkering researchers and less to be used in actual products.
Earlier quoted context omitted.
Yes, Hebel doesn't have a ton of features and a kitchen-sink of different models yet, but I hope that's going to change. There are lots of things that are quite easy to implement in the current framework, such as: - Neural net regression - Autoencoders - Restricted Boltzman machines There's a lot of interest for convolutional networks and the best way to implement it will be to wrap Alex Krizhevsky's cuda-convnet, li…
Yup, I didn't mean to belittle Hebel. I actually just meant that the lack of features is likely why I hadn't heard of it. From the looks of things it's on a nice path. You philisophy about what Hebel should be sound similar what's been done with MORB for making RBMs, and that is one of the reasons I've always like that library. Although MORB still does incur the 'working with theano' conceptual overhead.
Earlier quoted context omitted.
Yes, Hebel doesn't have a ton of features and a kitchen-sink of different models yet, but I hope that's going to change. There are lots of things that are quite easy to implement in the current framework, such as: - Neural net regression - Autoencoders - Restricted Boltzman machines There's a lot of interest for convolutional networks and the best way to implement it will be to wrap Alex Krizhevsky's cuda-convnet, li…
Question: do you/will you plan to support converting GPU nets to CPU, perhaps by keeping weights and architecture definition separate from PyCUDA dependent structures during serialization? I have found that using a trained net for preprocessing can be accomplished using very limited resources (read: Core 2 Duo laptop). This is one of the very nice features of DeCAF, which could allow for some interesting applications…
As far as embedded devices go (I assume you're talking about ARM cpus etc), they are probably too underpowered to run Neural nets anyway, or models would have to be written in highly specialized C.
Went to the docs page, looked for benchmarks, haven't found any. Went to the github page, looked for unit tests, haven't found any. Other than that, looks promising.
There are some unit tests in Hebel though [2], even though coverage is not complete.
[1] http://yann.lecun.com/exdb/mnist/ [2] https://github.com/hannes-brt/hebel/blob/master/hebel_test.p...
Earlier quoted context omitted.
But you must have an Nvidia card around some where to test your codes out first? It looks like the best bang for the buck is a GTX 760.
What types of applications are you guys typically doing with these neural nets? If there was an alternative to AWS which was cheaper / easier to set up would it be a compelling service to check out?