University of Cambridge > Talks.cam > Computational Neuroscience > Structured recognition for generative models with explaining away

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Structured recognition for generative models with explaining away

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Samuel Eckmann.

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 in the pattern of interactions between explanatory latent variables captured through a probabilistic graphical model. Although the learning of structured graphical models has a long history, much recent work in unsupervised modelling has instead emphasised flexible deep-network-based generation, either transforming independent latent generators to model complex data or assuming that distinct observed variables are derived from different latent nodes. Here, we extend the output of amortised variational inference to incorporate structured factors over multiple variables, able to capture the observation-induced posterior dependence between latents that results from “explaining away’’ and thus allow complex observations to depend on multiple nodes of a structured graph. We show that appropriately parameterised factors can be combined efficiently with variational message passing in elaborate graphical structures. We instantiate the framework based on Gaussian Process Factor Analysis models, and empirically evaluate its improvement over existing methods on synthetic data with known generative processes. We then fit the structured model to high-dimensional neural spiking time-series from the hippocampus of freely moving rodents, demonstrating that the model identifies latent signals that correlate with behavioural covariates.

This talk is part of the Computational Neuroscience series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

HowToMiners Trinity Hall History Society Art Cell Gallery

Other talks

Bradford Hill Seminar – Tackling Bias and Inequities in Health and Genomic Data Learning to work with Learning Machines Neural mechanisms of domain-general inhibitory control Retarded motile active matter Machine Learning Solutions to the Yang Baxter Equation Collective motion of colloidal particles with propulsion induced by time-delayed feedback
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity