Hi dear colleagues i have a couple of questions about deeplearning and practical usage of it.
I would like to know about the state of the art software and/or tools about deep learning specifically convolutional neural network and recurrent neural network divisions. For example if we have 1D time series data what deeplearning technologies should we concern? Another question having 500 640x480 8 bit gray level pistachio images how can we improve the classificiation accuracy if we want to apply CNN algortihm. Last thing what do you think about deeplearning4java? usage, efficiency, computation cost etc.
Thanks in advance.
On the software side, the following comes to mind:
http://www.cntk.ai/
https://www.tensorflow.org/
http://deeplearning.net/software/theano/#
http://deeplearning.net/software/pylearn2/
http://torch.ch/
I think and hope this could help
https://github.com/fagonzalezo/nn_nlp_tutorial
http://fagonzalezo.github.io/nn_nlp_tutorial/
Dear Musa, I would suggest you visit the following websites for information on the state-of-the-art software/tools about deep learning.
1. http://caffe.berkeleyvision.org/
2. http://deeplearning.net/
3. http://www.kdnuggets.com/2015/06/popular-deep-learning-tools.html
4. https://github.com/ChristosChristofidis/awesome-deep-learning
I hope this information would be help to you.
Good luck.
An evaluation of the deep learning toolkits can be found here:
https://github.com/zer0n/deepframeworks/blob/master/README.md
- Badges
- Science topic