Theoretical Motivations for Deep Learning | Rinu Boney

This post is based on the lecture “Deep Learning: Theoretical Motivations” given by Dr. Yoshua Bengio at Deep Learning Summer School, Montreal 2015. I highly recommend the lecture for a deeper understanding of the topic.

This post is based on the lecture “ Deep Learning: Theoretical Motivations ” given by Dr. Yoshua Bengio at Deep Learning Summer School, Montreal 2015 . I highly recommend the lecture for a deeper understanding of the topic. Deep learning is a branch of machine learning algorithms based on learning multiple levels of representation. The multiple levels of representation corresponds to multiple levels of abstraction. This post explores the idea that if we can successfully learn multiple levels of representation then we can generalize well. The below flow charts illustrate how the different parts

saved by

• Philip KAO

related reading

• Why Deep Learning Works – Key Insights and Saddle Points - KDnuggetskdnuggets.com
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugesarxiv.org
• Neural Networks, Types, and Functional Programming -- colah's blogcolah.github.io
• Statistical Mechanics of Deep Learningganguli-gang.stanford.edu
• The Little Book of Deep Learningfleuret.org
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• Elon Litman | Elements of a Vector Spaceelonlit.com
• The Decade of Deep Learning | Leo Gaobmk.sh
• Deep Learning is Not So Mysterious or Differentarxiv.org
• Understanding Deep Learningudlbook.github.io