Go Back

Photo of Richard Zemel

Richard Zemel

Richard Zemel’s research focuses on various aspects of machine learning, particularly unsupervised learning, boosting, and probabilistic networks. He studies applications such as image segmentation and collaborative filtering. He is also interested in neural coding, and has spent quite a bit of time working in the areas of perceptual learning, motion perception and visual attention.


New Opportunities Award, Canada Foundation for Innovation, 2002-2007.

Young Investigator Award, Office of Naval Research, 1998-2002.

National Sciences and Engineering Research Council Postgraduate Scholarship, 1989-1991.

Discovery Accelerator Supplement, National Sciences and Engineering Research Council

Relevant Publications

K. Xu et al, "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention," ICML-2015: The 32nd International Conference on Machine Learning, 2015.



Senior Fellow Learning in Machines & Brains


University of TorontoDepartment of Computer Science


PhD (Computer Science) University of Toronto

MSc (Computer Science) University of Toronto

BA (History and Science) Harvard University



Ideas Related to Richard Zemel

Research Brief | Learning in Machines & Brains

A machine learning system generates captions for images from scratch

Caption generation is a fundamental problem of artificial intelligence, one that distinguishes human intelligence – our ability to construct descriptions...


Neural networks advances improve machine translation

Breakthroughs in machine translation using neural networks have improved our ability to translate words and sentences between many languages. Researchers...

News | Learning in Machines & Brains

Computer model generates automatic captions for images

CIFAR fellows have created a machine learning system that generates captions for images from scratch, scanning scenes and putting together...