Hello everyone,
I am new in deep learning. I need a high performance deep learning base classifier for multi-classes classification problems. Would you please introduce me some state-of-the-art tools or frameworks?
I wish to say thank you in advance for your generous support.
Find out about Azure Machine learning. It can help you in doing deep learning with little programming.
Hi ,
You may start with a simple digits classifications example using matlab. You can download a 30 day trail version of matlab 2015. The below link has a clear explanation about the code in simple terms.
Hope this helps.
http://au.mathworks.com/help/nnet/examples/training-a-deep-neural-network-for-digit-classification.html
http://au.mathworks.com/help/nnet/examples/training-a-deep-neural-network-for-digit-classification.html
How about starting with Tensorflow? or Theano? it will be a good start starting with some datasets like MNIST.
Conference Paper HDLTex: Hierarchical Deep Learning for Text Classification
here is Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. Deep learning models have achieved state-of-the-art results across many domains. RMDL solves the problem of finding the best deep learning structure and architecture while simultaneously improving robustness and accuracy through ensembles of deep learning architectures.
Preprint RMDL: Random Multimodel Deep Learning for Classification
- Badges
- Science topic