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
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
- Neural Networks, Types, and Functional Programming -- colah's blogcolah.github.io
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugesarxiv.org
- The Little Book of Deep Learningfleuret.org
- Statistical Mechanics of Deep Learningganguli-gang.stanford.edu
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
- The Decade of Deep Learning | Leo Gaobmk.sh
- Understanding Deep Learningudlbook.github.io
- Deep Learning is Not So Mysterious or Differentarxiv.org
- Understanding deep learning requires rethinking generalizationarxiv.org