Talk
Attentive Recurrent Comparators
Pranav Shyam · Shubham Gupta · Ambedkar Dukkipati

Mon Aug 7th 05:15 -- 05:33 PM @ Parkside 1

Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making observations. Using the representations extracted by ARCs, we develop a way of approximating a \textit{dynamic representation space} and use it for one-shot learning. In the task of one-shot classification on the Omniglot dataset, we achieve the state of the art performance with an error rate of 1.5\%. This represents the first super-human result achieved for this task with a generic model that uses only pixel information.

Author Information

Pranav Shyam (R. V. College of Engineering & Indian Institute of Science)
Shubham Gupta (Indian Institute of Science)
Ambedkar Dukkipati (Indian Institute of Science)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors