CCIMI lecturer Hamza Fawzi, along with Frank Kelly (University of Cambridge Statistical Laboratory), and Damon Wischik (University of Cambridge Computer Laboratory) are beginning a study group on Mathematics of Machine Learning.
Algorithms for machine learning, especially deep neural networks, have had astounding success at tasks like image recognition and machine translation. Their standard training method is backpropagation, introduced by Geoff Hinton in 1986, and their success has been fuelled by huge datasets and ever-faster computers. But training is still an art rather than a science, and Hinton now says “My view is throw it all away and start again.”
The Mathematics and Machine Learning study group will explore
What makes neural networks work so well?
Which applications are straining the limits of backpropagation?
What new forms of optimization / training can we devise?
What design of computer systems will be needed?
It will involve a mix of tutorials, applications, and theory. It is intended for mathematicians, computer scientists, and all other areas of data science.
The group will begin meeting on Tuesday 24 October, and more information can be found at www./talks.cam.ac.uk/show/index/72891