Information Theory, Pattern Recognition, and Neural Networks

Course Videos

We recommend viewing the videos online (synchronised with snapshots and slides) at the video lectures website.

Alternatively, the videos can be downloaded using the links below. We recommend using VLC to view them.

Lecture Title Date/Time Videos Snapshots Slides
Bonus Counting (labelled unrooted) trees 06 Feb 2012, 16.00 00.f4v [ 46M] 00.pdf [6.1M] 00.html
Lecture 1 Introduction to Information Theory 20 Feb 2012, 16.00 01.mp4 [675M] 01.pdf [ 16M] 01.html
Lecture 2 Entropy and Data Compression (I):
Introduction to Compression, Information Theory
and Entropy
27 Feb 2012, 14.30 02.mp4 [564M] 02.pdf [ 26M] 02.html
Lecture 3 Entropy and Data Compression (II):
Shannon's Source Coding Theorem, The Bent Coin Lottery
05 Mar 2012, 14.30 03.mp4 [561M] 03.pdf [ 14M] 03.html
Lecture 4 Entropy and Data Compression (III):
Shannon's Source Coding Theorem, Symbol Codes
16 Apr 2012, 14.30 04.mp4 [605M] 04.pdf [ 13M] 04.html
Lecture 5 Entropy and Data Compression (IV):
Shannon's Source Coding Theorem, Symbol Codes and
Arithmetic Coding
23 Apr 2012, 14.30 05.mp4 [670M] 05.pdf [ 26M] 05.html
Lecture 6 Noisy Channel Coding (I):
Inference and Information Measures for Noisy Channels
30 Apr 2012, 14.30 06.mp4 [588M] 06.pdf [ 22M] 06.html
Lecture 7 Noisy Channel Coding (II):
The Capacity of a Noisy Channel
07 May 2012, 14.30 07.mp4 [499M] 07.pdf [ 34M] 07.html
Lecture 8 Noisy Channel Coding (III):
The Noisy-Channel Coding Theorem
21 May 2012, 14.30 08.mp4 [745M] 08.pdf [ 28M] 08.html
Lecture 9 A Noisy Channel Coding Gem, and
An Introduction to Bayesian Inference (I)
28 May 2012, 14.30 09.mp4 [535M] 09.pdf [ 46M] 09.html
Lecture 10 An Introduction To Bayesian Inference (II):
Inference Of Parameters and Models
28 May 2012, 15.30 10.mp4 [825M] 10.pdf [ 43M] 10.html
Lecture 11 Approximating Probability Distributions (I):
Clustering As An Example Inference Problem
11 Jun 2012, 14.30 11.mp4 [629M] 11.pdf [ 27M] 11.html
Lecture 12 Approximating Probability Distributions (II):
Monte Carlo Methods (I):
Importance sampling, rejection sampling,
Gibbs sampling, Metropolis method
11 Jun 2012, 15.30 12.mp4 [908M] 12.pdf [ 51M] 12.html
Lecture 13 Approximating Probability Distributions (III):
Monte Carlo Methods (II):
Slice sampling, Hybrid Monte Carlo,
Over-relaxation, Exact Sampling
25 Jun 2012, 14.30 13.mp4 [1.1G] 13.pdf [ 57M] 13.html
Lecture 14 Approximating Probability Distributions (IV):
Variational Methods
09 Jul 2012, 14.30 14.mp4 [512M] 14.pdf [ 46M] 14.html
Lecture 15 Data Modelling With Neural Networks (I):
Feedforward Networks:
The Capacity Of A Single Neuron, Learning As Inference
09 Jul 2012, 15.30 15.mp4 [950M] 15.pdf [ 92M] 15.html
Lecture 16 Data Modelling With Neural Networks (II):
Content-Addressable Memories And
State-Of-The-Art Error-Correcting Codes
16 Jul 2012, 14.30 16.mp4 [1.0G] 16.pdf [ 66M] 16.html

  Course page

  Other course materials - free online text book [Information Theory, Inference, and Learning Algorithms] - software - further links - and errata

  Our workflow, describing how the videos were recorded.