# AI6 Cycle 1 Learning Materials

Pytorch
Learning materials for AI6 Pytorch.

Stanford STAT385 Theories of Deep Learning
For discussions about the weekly lectures and readings for Stanford STAT385 Theories of Deep Learning (<a href="https://stats385.github.io">https://stats385.github.io</a>). Links to the original recorded lecture videos and readings for each week will be posted here.

Berkeley CS294 Deep Reinforcement Learning
For discussions about the materials from UC Berkeley CS294 on Deep Reinforcement Learning (<a href="http://rll.berkeley.edu/deeprlcoursesp17/">http://rll.berkeley.edu/deeprlcoursesp17/</a>)

Fast.AI
<a href="http://fast.ai">fast.ai</a> v2 has their own forums so we would be repeating it here, but here’s the link to <a href="http://fast.ai">fast.ai</a> v2 resources: <a href="http://forums.fast.ai/t/welcome-to-part-1-v2/5787">http://forums.fast.ai/t/welcome-to-part-1-v2/5787</a>

Wiki: Lecture 2 – Overview of Deep Learning from a Practical Point of View
[Stanford STAT385 Theories of Deep Learning]
(3)

Wiki: Discussion on STAT385 Lecture 1 Video and Readings
[Stanford STAT385 Theories of Deep Learning]
(1)

Wiki: Lecture 8 – Topology and Geometry of Half-rectified Network Optimization
[Stanford STAT385 Theories of Deep Learning]
(1)

Wiki: Lecture 7 – Understanding and Improving Deep Learning With Random Matrix Theory
[Stanford STAT385 Theories of Deep Learning]
(1)

Wiki: Lecture 6 – Views of Deep Networks from Reproducing Kernel Hilbert Spaces
[Stanford STAT385 Theories of Deep Learning]
(1)