Machine Learning (2015, University of Oxford)

Machine Learning (2015, University of Oxford). Instructor: Professor Nando de Freitas. Machine learning techniques enable us to automatically extract features from data so as to solve predictive tasks, such as speech recognition, object recognition, machine translation, question-answering, anomaly detection, medical diagnosis and prognosis, automatic algorithm configuration, personalisation, robot control, time series forecasting, and much more. Learning systems adapt so that they can solve new tasks, related to previously encountered tasks, more efficiently.

The course focuses on the exciting field of deep learning. By drawing inspiration from neuroscience and statistics, it introduces the basic background on neural networks, back propagation, Boltzmann machines, autoencoders, convolutional neural networks and recurrent neural networks. It illustrates how deep learning is impacting our understanding of intelligence and contributing to the practical design of intelligent machines.

Lecture 11 - Max-margin Learning, Transfer and Memory Networks

Go to the Course Home or watch other lectures:

Lecture 01 - Introduction
Lecture 02 - Linear Prediction
Lecture 03 - Maximum Likelihood
Lecture 04 - Regularizers, Basis Functions and Cross-validation
Lecture 05 - Regularizers, Basis Functions and Cross-validation (cont.)
Lecture 06 - Optimisation
Lecture 07 - Logistic Regression
Lecture 08 - Modular Backpropagation, Logistic Regression and Torch
Lecture 09 - Neural Networks and Modular Design in Torch
Lecture 10 - Convolutional Neural Networks
Lecture 11 - Max-margin Learning, Transfer and Memory Networks
Lecture 12 - Recurrent Neural Networks and LSTMs
Lecture 13 - Generation Sequences with Recurrent Neural Networks by Alex Graves
Lecture 14 - Variational Autoencoders and Deep Recurrent Attentive Writers by Karol Gregor
Lecture 15 - Reinforcement Learning with Direct Policy Search
Lecture 16 - Reinforcement Learning and Neuro-dynamic Programming