Day 1: Fundamentals of Deep Learning I
Read before class on Monday, June 8, 2020
- Machine Learning for Beginners: An Introduction to Neural Networks - A simple explanation of how they work and how to implement one from scratch in Python
- The Matrix Calculus You Need For Deep Learning paper by Terence Parr and Jeremy Howard
- Artificial Intelligence book: Linear Algebra - basics of linear algebra
- Dive into Deep Learning book: 3-Gradient.pdf - Gradient and Auto Differentiation
- MIT Introduction to Deep Learning | 6.S191 - Main concepts of deep learning, gradient descent, backpropagation
- Series of eight video lectures on the math of machine learning by Tinnam Ganesh. “Elements of Neural Networks & Deep Learning”, Part1,2,3 - Details of gradient descent, backpropagation
- Read on forward and back propagation algorithm, step-by-step guide, https://www.analyticsvidhya.com/blog/2017/05/neural-network-from-scratch-in-python-and-r/, implement and understand the R code of the algorithm
- Paper: Angermueller et al., “Deep Learning for Computational Biology.” - Review on machine learning, (epi)genomics examples. Supervised vs. unsupervised learning. Deep neural networks. Box 1 - network basics. Box 2 - convolutional NN. TOOLS: Caffe, Theano, Torch7, TensorFlow. Data preparation, model training and optimization
- Paper: Pérez-Enciso, and Zingaretti. “A Guide for Using Deep Learning for Complex Trait Genomic Prediction.” Genes, 2019 - Deep learning for predicting phenotypes from genomics data. Deep learning basics, definitions