Subscribe to DSC Newsletter

Course material for 2014-1015. 


Lecture 1: Introduction slides Video 
Lecture 2: Linear prediction slides Video 
Lecture 3: Maximum likelihood slides.pdf Video 
Lectures 4 & 5: Regularizers, basis functions and cross-validation slides.pdf Video 1 Video 2 
Lecture 6: Optimisation slides.pdf Video 
Lecture 7: Logistic regression slides.pdf Video 
Lecture 8: Back-propagation and layer-wise design of neural nets slides.pdf Video 
Lecture 9: Neural networks and deep learning with Torch slides.pdf Video 
Lecture 10: Convolutional neural networks slides.pdf Video 
Lecture 11: Max-margin learning and siamese networks slides.pdf Video 
Lecture 12: Recurrent neural networks and LSTMs slides.pdf Video 
Lecture 13: Hand-writing with recurrent neural networks (Guest speaker: Alex Graves from Google Deepmind) 
Lecture 14: Variational autoencoders and image generation (Guest speaker: Karol Gregor from Google Deepmind) 
Lecture 15: Reinforcement learning with direct policy search slides.pdf 
Lecture 16: Reinforcement learning with action-value functions slides.pdf 


Please click on Timetables on the right hand side of this page for time and location of the practicals. The instructors are Brendan Shillingford and Marcin Moczulsky.

Practicals will use Torch, a powerful programming framework for deep learning that is very popular at Google and Facebook research.

Practical on week 2: (1) Learning Lua and the tensor library. pdf 
Practical on week 3: (2) Online and batch linear regression. pdf 
Practical on week 4: (3) Logistic regression and optimization. pdf 
Practical on week 5: continued previous practical. 
Practical on week 6: (4) Feedforward neural networks, and implementing your own layer. pdf 
Practical on week 7: (5) Intro to nngraph for graph-shaped modules. pdf
Practical on week 8: (6) Training a LSTM language model. pdf
See the Github repository list for the practicals' code and technical instructions. 


Please click on Timetables on the right hand side of this page for time and location of the classes. The exercises appear below and are due Thursdays at 1pm on the specified week.

Class on Week 3Problem set. Due 1pm Thursday of Week 2.
Class on Week 5Problem set. Due 1pm Thursday of Week 4.
Class on Week 7Problem set. Due 1pm Thursday of Week 6.
Class on Week 8Problem set. Due 1pm Thursday of Week 7.

Click here for more information.

DSC Resources

Additional Reading

Follow us on Twitter: @DataScienceCtrl | @AnalyticBridge

Views: 7249

Follow Us

On Data Science Central

On DataViz

On Hadoop

© 2017 is a subsidiary and dedicated channel of Data Science Central LLC   Powered by

Badges  |  Report an Issue  |  Terms of Service