Day 2: Fundamentals of Deep Learning II
MIT Deep Learning Basics: Introduction and Overview with TensorFlow - a blog post with infografics and brief description of each type of neural network, links to Lex Fridman’s video lectures
Dive into Deep Learning book: 4-Linear-Methods.pdf - Linear regression and gradient descent
Deep Learning book: 4 Numerical Computation - Gradiend descent, optimization. Full Part I: Applied Math and Machine Learning Basics is recommended
Neural Networks and Deep Learning book: Chapter 2 - details the math of backpropagation
Zou, James, Mikael Huss, Abubakar Abid, Pejman Mohammadi, Ali Torkamani, and Amalio Telenti. “A Primer on Deep Learning in Genomics.” Nature Genetics, 2018 - Deep learning in genomics overview (feed-forward, convolutional, recurrent) and a Python tutorial on detecting DNA motifs. Box 1 and 2 - concepts and definitions. Box 3 - online resources (cloud platforms, GPU services, software libraries, educational resources, more). https://github.com/abidlabs/deep-learning-genomics-primer
Topol, Eric J. “High-Performance Medicine: The Convergence of Human and Artificial Intelligence.” Nature Medicine, 2019 - AI and deep learning examples in medicine. Publications comparing AI with doctors, FDA-approved AI algorithms. Pathology (cancer, dermatology, ophtalmology, gastroenterology, mental health). Benefits and biases
How Backpropagation Works - 18min video by Brandon Rohrer explaining backpropagation using shower heads
An overview of gradient descent optimization algorithms by Sebastian Ruder. Details and math of individual algorithms