Walker, william; Soulat, hugo; Yu, changmin; Sahani, Maneesh; (2023) Unsupervised representation learning with recognition-parametrised probabilistic models. In: Proceedings of the 26th International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research: Valencia, Spain Proceedings of Machine Learning Research. (In press).

Preview

Text walker-soulat-etal-2023-aistats.pdf - Published Version Download (6MB) | Preview

Abstract

We introduce a new approach to probabilistic unsupervised learning based on the recognitionparametrised model (RPM): a normalised semiparametric hypothesis class for joint distributions over observed and latent variables. Under the key assumption that observations are conditionally independent given latents, the RPM combines parametric prior and observation-conditioned latent distributions with non-parametric observation marginals. This approach leads to a flexible learnt recognition model capturing latent dependence between observations, without the need for an explicit, parametric generative model. The RPM admits exact maximum-likelihood learning for discrete latents, even for powerful neuralnetwork-based recognition. We develop effective approximations applicable in the continuouslatent case. Experiments demonstrate the effectiveness of the RPM on high-dimensional data, learning image classification from weak indirect supervision; direct image-level latent Dirichlet allocation; and recognition-parametrised Gaussian process factor analysis (RP-GPFA) applied to multi-factorial spatiotemporal datasets. The RPM provides a powerful framework to discover meaningful latent structure underlying observational data, a function critical to both animal and artificial intelligence.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as CSVJSONXML

Archive Staff Only

View Item