4 citations · 12 across the 9 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.LG2022
Unsupervised representation learning with recognition-parametrised probabilistic models
William I. Walker, Hugo Soulat, Changmin Yu +1
We introduce a new approach to probabilistic unsupervised learning based on the recognition-parametrised model (RPM): a normalised semi-parametric hypothesis class for joint distri…
cs.LG2022★ 2 cited
Structured Recognition for Generative Models with Explaining Away
Changmin Yu, Hugo Soulat, Neil Burgess +1
A key goal of unsupervised learning is to go beyond density estimation and sample generation to reveal the structure inherent within observed data. Such structure can be expressed…
cs.LG2022
SEREN: Knowing When to Explore and When to Exploit
Changmin Yu, David Mguni, Dong Li +3
Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states. To enc…