gneuralnetwork
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Gneuralnetwork] Updated Example


From: Jean Michel Sellier
Subject: Re: [Gneuralnetwork] Updated Example
Date: Sun, 24 Jul 2016 09:15:05 +0200

Hi David,

What you have done is really great! Thank you so much for this contribution!

Once you are done with the clean up and you feel comfortable with the code, we could release it online. Just let me know when you feel ready.

I really like the direction Gneural Network is taking thanks to you!

Best,

JM


On Jul 23, 2016 10:34 PM, "David Mascharka" <address@hidden> wrote:
Hi everybody,

I've had a little bit of time to play around with my idea. See https://github.com/davidmascharka/neural-net-playing/blob/master/layer.c for an example of a multi-layer network. There's some cleanup and restructuring to do, especially to make it extensible, but this showcases the idea.

I've got derivatives in for the network so it does learn with linear, tanh, softmax, and relu nonlinearities. I'd like to add a simple convolutional example (like LeNet learning to do MNIST handwritten digit recognition -- common benchmark for computer vision) to show this is actually useful.

What do you all think? Do you think this is a useful direction for Gneural Network to move? I'm really excited about the project and the possibilities. I'm also really enjoying working with C - Python and its libraries are painful to work with.

Best,
David

reply via email to

[Prev in Thread] Current Thread [Next in Thread]