Presented by: David Balduzzi, Victoria University Wellington

Deep learning has yielded spectacular breakthroughs, recently surpassing human performance in object recognition, Atari games and the board game Go. In this talk I will give a high-level overview of the mathematical foundations of deep learning, focusing on how gradients are computed and controlled. I will discuss the problems of vanishing, exploding and shattering gradients, and techniques that have been developed to ameliorate them in very deep networks. Finally, time-permitting, I will discuss convergence guarantees for neural nets.

About Maths Colloquium

The Mathematics Colloquium is directed at students and academics working in the fields of pure and applied mathematics, and statistics. 

We aim to present expository lectures that appeal to our wide audience.

Information for speakers

Information for speakers

Maths colloquia are usually held on Mondays, from 2pm to 3pm, in various locations at St Lucia.

Presentations are 50 minutes, plus five minutes for questions and discussion.

Available facilities include:

  • computer 
  • data projector
  • chalkboard or whiteboard

To avoid technical difficulties on the day, please contact us in advance of your presentation to discuss your requirements.