Home

Learning Resources

(Much of this content borrowed from the sunny-side-up wiki)

Deep learning

• Learning about deep learning

• Understanding LSTM Networks, August 2015, Christopher Olah: "Long Short Term Memory networks – usually just called 'LSTMs' – are a special kind of RNN, capable of learning long-term dependencies."

• A Few Useful Things to Know about Machine Learning, 2012, Pedro Domingos, University of Washington Computer Science

• Understanding Convolution in Deep Learning: "Convolution is probably the most important concept in deep learning right now. ... But what makes convolution so powerful? How does it work?"

• Conv Nets: A Modular Perspective

• [The Unreasonable Effectiveness of Recurrent Neural Networks] (http://karpathy.github.io/2015/05/21/rnn-effectiveness/): An instant classic--train your own recurrent neural networks in Python, from the ground up.

• Practical Recommendations for Gradient-Based Training of Deep Archtiectures

• Learning Deep Architectures for AI (Book)

• Tips for training CNNs

• Udacity deep learning course

Natural Language Processing

• For starters: NLP with Roger Ebert

• This blog post has a super barebones but comprehensive overview

• The scikit-learn feature extraction page is a surprisingly rich resource on commonly used NLP techniques.

• NLP in the Kitchen, an LATimes (!) blog post

• Stanford NLP Coursera videos

• UMichigan NLP Coursera

• Natural Language Processing with Python (book; free or from Safari Books)