Deep Meta-Learning

Monday 30 January 2017, 2.00PM to 15:00

Speaker(s): Dr Charles Blundell, DeepMind

Synopsis

Recently deep learning methods have attained super-human performance on a wide range of tasks, from image classification to game playing. A common limitation of these methods is a requirement for a large amount of data from each new task.

Meta-learning provides a potential means of overcoming this limitation, where the general principles learnt on one task may be re-used to learn a new task more efficiently than starting from scratch.

I shall describe recent work we have done on learning to learn in the context of deep neural networks applied to image classification and reinforcement learning tasks.

Biography

Charles Blundell is a staff research scientist at DeepMind. He completed his PhD in machine learning at the Gatsby Unit, UCL, and before that studied computer science at York.

Location: PT005

Admission: Free

Email: helen.m.smith@york.ac.uk

Telephone: 4485

Administrative Enquiries:

Please contact Helen Fagan, Postgraduate Office, for more information.

Links:

Electronics Department Student Seminars

Chemistry Department Seminars

Computer Science Department Seminars

Physics Department Seminars

Events

For past events please see the relevant year: 
2016 | 2015 | 2014 | 2013 | 2012

Student Seminars

The Department also runs a programme of Research Student Seminars given by PhD students in their 3rd year of study.