InfoCoBuild

CPSC 540: Machine Learning

CPSC 540: Machine Learning (2013, University of British Columbia). Instructor: Professor Nando de Freitas. This is a graduate-level course on machine learning, a field that focuses on using automated data analysis for tasks like pattern recognition and prediction. Topics will (roughly) include linear models, density estimation, graphical models, Bayesian methods, deep learning, online/active/causal learning, reinforcement learning, and learning theory.

Lecture 14 - Unconstrained Optimization


Go to the Course Home or watch other lectures:

Lecture 01 - Introduction to Machine Learning
Lecture 02 - Linear Prediction
Lecture 03 - Maximum Likelihood and Linear Regression
Lecture 04 - Regularization and Regression
Lecture 05 - Regularization, Cross-validation and Data Size
Lecture 06 - Bayesian Learning
Lecture 07 - Bayesian Learning (cont.)
Lecture 08 - Introduction to Gaussian Processes
Lecture 09 - Gaussian Processes
Lecture 10 - Bayesian Optimization and Multi-armed Bandits
Lecture 11 - Decision Trees
Lecture 12 - Random Forests
Lecture 13 - Random Forests Applications
Lecture 14 - Unconstrained Optimization
Lecture 15 - Logistic Regression and Neuron Models
Lecture 16
Lecture 17 - Neural Networks
Lecture 18 - Deep Learning
Lecture 19 - Deep Learning (cont.), Google Autoencoders and Dropout
Lecture 20 - Importance Sampling and Markov Chain Monte Carlo (MCMC)
Lecture 21 - Markov Chain Monte Carlo (MCMC) II