learning_resources

PDF's & Links to lecture slides/papers/topics helpful for learning RL/ML/DL/Scientific Computing in my other repos. This is not a complete list, but it does have some gems I found very useful in my own journey.

Scientific Computing/Applied Linear Algebra

(too many links. B. Welfert has made MAT 421 F2019, Numerical Methods a tough one.)

Reinforcement Learning & Classic Learning concepts

Neural Networks for Machine Learning (Lecture 6a @ UToronto), G. Hinton: cs.tornonto.edu

On the importance of initialization and momentum in deep learning (paper), G. Hinton: cs.tornonto.edu

Adversarial Attacks on Neural Network Policies (paper), P. Abbeel: arXiv

Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms? (paper), A. Madry: arXiv

Optimal Control (Lecture @ ASU), Y. Ren: designinformaticslab

Reinforcement Learning (Lecture 14 @ Stanf), FF Li: cs231n

Python/Numpy Tutorial for Computer Vision (Lecture @ Stanf), J. Johnson: cs231n

Adversarial Machine Learning Reading List (Researcher Blog), N. Carlini: nicholas.carlini

Human Level Control Through Deep Reinforcement Learning, V. Mnih: pdf@stanf

Deep Learning, Y. LeCun & Y. Bengio & G. Hinton: nature

Backpropagation Algorithm (Derivation), {several contributors}: brilliant.org

RL by David Silver

AlexNet, VGG-16

Time Series Classification/Dynamic Programming

Time Series Classification, a dedicated homepage, which has datasets, algorithms, and researchers. This site put me on a serious spiral.

Deep learning for time series classification: a review, H. Fawaz: arXiv

Dynamic Programming Algorithm Optimization for Spoken Word Recognition, H. Sakoe & S. Chiba: irit.fr

How DTW (Dynamic Time Warping) algorithm works, T. Körting: youtube

Programatically understanding dynamic time warping (DTW) ipynb, N. Batra: github

Robotics

Fast, Autonomous Flight in GPS-Denied andCluttered Environments, K. Mohta: arXiv. Includes powerpoint that is my report on this for jdas and pdf