Supervised Machine Learning Review
A lecture that reviews ideas from supervised machine learning that are relevant for understanding deep neural networks. Includes the statistical machine learning framework, principles for selecting loss functions, and the bias-variance tradeoff. The lecture ends with the surprising double-descent behavior that neural networks can perform well even when highly overparameterized.
This lecture is from Northeastern University's CS 7150 Summer 2020 class on Deep Learning, taught by Paul Hand.
The notes are available at: http://khoury.northeastern.edu/home/hand/teaching/cs7150-summer-2020/Supervised_Machine_Learning_Review.pdf
Видео Supervised Machine Learning Review канала Paul Hand
This lecture is from Northeastern University's CS 7150 Summer 2020 class on Deep Learning, taught by Paul Hand.
The notes are available at: http://khoury.northeastern.edu/home/hand/teaching/cs7150-summer-2020/Supervised_Machine_Learning_Review.pdf
Видео Supervised Machine Learning Review канала Paul Hand
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Unlearned Neural Networks as Image Priors for Inverse Problems
Rectangle of maximal area.mp4
Generative Adversarial Networks
Paul Hand - Determined
Carbon Storage Demo - Tapia Camps at Rice University
Most movies are boring -- Paul E. Hand
Neural Network Architectures for Images
Gradient Descent and Stochastic Gradient Descent
Continual Learning and Catastrophic Forgetting
Invertible Neural Networks and Inverse Problems
Variational Autoencoders
Adversarial Examples for Deep Neural Networks
Theory of GANs for Compressed Sensing
Architectural Elements Of Neural Networks
Path of Steepest Descent.mp4
Rectangular prism of maximal volume.mp4
Choice of coordinates for inscribed triangle.mp4