Useful Resources

Books

• Michael Nielsen: Neural Networks and Deep Learning
• Goodfellow, Bengio and Courville: Deep Learning
• Simon Prince: Computer Vision models
• Computer Vision: Algorithms and Applications

Conferences

• CVPR: http://cs.stanford.edu/people/karpathy/cvpr2015papers/
• NIPS: http://papers.nips.cc/book/advances-in-neural-information-processing-systems-27-2014

Lectures

• http://cs231n.github.io/
• http://cs229.stanford.edu/materials.html
• http://www.seas.harvard.edu/courses/cs281/

MOOCs

• https://www.udacity.com/course/deep-learning--ud730 (offered by Google)

Blogs

• Christopher Olah’s blog contains many well-written and nicely illustrated explanations to basic deep learning topics.
• Andrej Kapathy
• Andrej Kapathy: A Hacker’s Guide to Neural Networks
• Ferenc Huszár: Rather strong focus on generative models involving sophisticated mathematics (mostly statistics).
• Distill: Journal-like website with interactive explanations.
• Explained Visually: Visual explanations of some machine learning topics.
• Lol’Log: Explains and compares various new techniques in deep learning.
• off the convex path: Blog focussing on theoretical ML

Software

• Keras https://keras.io
• Tensorflow: https://www.tensorflow.org/
• Caffe: http://caffe.berkeleyvision.org/
• PyTorch: http://pytorch.org/
• Theano: http://deeplearning.net/software/theano/ (deprecated)