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

GNU Gneural Network

gnu.org

Post reply on HN
Print view View original

11–20 of 111 posts

Re: GNU Gneural Network

#11

Post by jjawssd »

semisight wrote: post #6
_delirium wrote: post #3

I agree with the general motivation that having too much AI research in the hands of software companies who keep it proprietary harms transparency and progress. But there is already a lot of neural-network free software, so why another package? For example, these widely used packages are free software, and seemingly more featureful: http://torch.ch/ , http://www.deeplearning.net/software/theano/ , http://pybrain.org/…

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

Gneural will compete with Theano sort of like how the GNU Hurd competes with Linux

Re: GNU Gneural Network

#12

Post by latenightcoding »

perfectfire wrote: post #9
latenightcoding wrote: post #7

Love it! If you want to play with state-of-the-art machine learning software, this is not for you. But if you want a clean implementation of neural networks in C that has a GPL license and no non-free components, this is a good start.

There's already FANN: which is more mature and has bindings for 28 other languages: http://leenissen.dk/fann/wp/language-bindings/ I maintain the C# wrapper.

I have used FANN from Perl, amazing library. I'm still glad there is some AI software under GNU's belt and the source code for "gneural networks" is pure C and way easier to follow (for now)

Re: GNU Gneural Network

#13

Post by revelation »

spdustin wrote: post #8
semisight wrote: post #6

Earlier quoted context omitted.

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

I'd really like to understand the reasons behind the focus on CUDA and not OpenCL. My understanding is that nVidia and AMD made sure their hardware and software would make the GPU accessible for non-graphics tasks, but AMD's version is not functionally or legally locked to their hardware. Why hasn't OpenCL taken off and run on nVidia hardware? It seems like there must be more at play, but I'll admit a lack of insight…

Because it requires nVidias cooperation in implementing OpenCL. And of course they are not about to do so in a useful manner when they are leading with CUDA.

Also, the premise of OpenCL is somewhat faulty. You end up optimizing for particular architectures regardless.

Re: GNU Gneural Network

#14

Post by albertzeyer »

semisight wrote: post #6
_delirium wrote: post #3

I agree with the general motivation that having too much AI research in the hands of software companies who keep it proprietary harms transparency and progress. But there is already a lot of neural-network free software, so why another package? For example, these widely used packages are free software, and seemingly more featureful: http://torch.ch/ , http://www.deeplearning.net/software/theano/ , http://pybrain.org/…

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

Wrong, most do support OpenCL or at least have partial support. It's just much less supported because not so much people see too much benefit from it. Btw, it's all open source. If you miss some functionality, it's really easy to add.

Re: GNU Gneural Network

#15

Post by microtonal »

spdustin wrote: post #8
semisight wrote: post #6

Earlier quoted context omitted.

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

I'd really like to understand the reasons behind the focus on CUDA and not OpenCL. My understanding is that nVidia and AMD made sure their hardware and software would make the GPU accessible for non-graphics tasks, but AMD's version is not functionally or legally locked to their hardware. Why hasn't OpenCL taken off and run on nVidia hardware? It seems like there must be more at play, but I'll admit a lack of insight…

It seems like there must be more at play, but I'll admit a lack of insight and imagination on this one.

I think the reasons are twofold: 1. CUDA had a big headstart over OpenCL. 2. NVIDIA has invested a lot in great libraries for scientific computing. E.g. for neural nets, they have made a library of primitives on top of CUDA for neural nets (cuDNN), which has been adopted by all the major packages.

Re: GNU Gneural Network

#16

Post by microtonal »

semisight wrote: post #6
_delirium wrote: post #3

I agree with the general motivation that having too much AI research in the hands of software companies who keep it proprietary harms transparency and progress. But there is already a lot of neural-network free software, so why another package? For example, these widely used packages are free software, and seemingly more featureful: http://torch.ch/ , http://www.deeplearning.net/software/theano/ , http://pybrain.org/…

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

I don't see the point either. Gneural will probably never be better than Theano, Torch, Tensorflow, Caffe, et al., which are already open. If anything, time/resources are much better invested in contributing to a polished/competitive OpenCL backend to one of these packages.

Re: GNU Gneural Network

#17

Post by raverbashing »

semisight wrote: post #6
_delirium wrote: post #3

I agree with the general motivation that having too much AI research in the hands of software companies who keep it proprietary harms transparency and progress. But there is already a lot of neural-network free software, so why another package? For example, these widely used packages are free software, and seemingly more featureful: http://torch.ch/ , http://www.deeplearning.net/software/theano/ , http://pybrain.org/…

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

Yeah, you don't depend on CUDA/cuDNN, but of course you can use them if you want it to be fast

But the CPU fallback is there

Re: GNU Gneural Network

#18

Post by typon »

jjawssd wrote: post #11
semisight wrote: post #6

Earlier quoted context omitted.

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

Gneural will compete with Theano sort of like how the GNU Hurd competes with Linux

In other words, not at all

Re: GNU Gneural Network

#19

Post by perfectfire »

semisight wrote: post #6
_delirium wrote: post #3

I agree with the general motivation that having too much AI research in the hands of software companies who keep it proprietary harms transparency and progress. But there is already a lot of neural-network free software, so why another package? For example, these widely used packages are free software, and seemingly more featureful: http://torch.ch/ , http://www.deeplearning.net/software/theano/ , http://pybrain.org/…

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

FANN is GNU licensed (LGPL 2.1), doesn't rely on non-free software, is written in C,so it's the same as Gneural in those regards. But it also is way more mature, has more features, compiles and runs on Linux, Windows and MacOS,and has bindings to 28 other languages.

Re: GNU Gneural Network

#20

Post by osense »

spdustin wrote: post #8
semisight wrote: post #6

Earlier quoted context omitted.

Almost all of the open source software in the area is permissive-licensed, and relies on non-free components (CUDA). To be honest, I'm not sure how Gneural plans to compete with those packages without support from CUDA or cuDNN, all of which are distinctly not open source.

I'd really like to understand the reasons behind the focus on CUDA and not OpenCL. My understanding is that nVidia and AMD made sure their hardware and software would make the GPU accessible for non-graphics tasks, but AMD's version is not functionally or legally locked to their hardware. Why hasn't OpenCL taken off and run on nVidia hardware? It seems like there must be more at play, but I'll admit a lack of insight…

I recall hearing that CUDA has much more mature tooling. Not only the already mentioned cuDNN, but the CUDA Toolkit [0] seems like a really comprehensive set of tools and libraries to help you with pretty much anything you might want to compute on a GPU.

Also somewhat related: AMD seems to be moving towards supporting CUDA on its GPUs in the future: http://www.amd.com/en-us/press-releases/Pages/boltzmann-init...

[0] https://developer.nvidia.com/cuda-toolkit

Post reply on HN