Data Efficiency and Machine Learning

[edit]

at Entropy Day, University of Sheffield on May 23, 2016 [pdf]
Neil D. Lawrence, University of Sheffield

Abstract

Entropy is a key component of information and probability, and may provide the key to data efficient learning. While we’ve seen great success with the AlphaGo computer program and strides forward in image and speech recognition our current machine learning systems are incredibly data inefficient. Better understanding of entropy with in these systems may provide the key to data efficient learning.

Links