University of Cambridge > Talks.cam > Computational Neuroscience > Certain about uncertainty? Latent representations of VAEs optimized for visual tasks.

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹ️ Information

Certain about uncertainty? Latent representations of VAEs optimized for visual tasks.

Download to your calendar using vCal

If you have a question about this talk, please contact Daniel Kornai .

Deep Learning methods are increasingly becoming instrumental as modeling tools in Computational Neuroscience, employing optimality principles to build bridges between neural responses and perception or behavior. Deep Generative Models (DGMs) can learn flexible latent variable representations of images while avoiding intractable computations, common in Bayesian inference. However, investigating the properties of inference in Variational Autoencoders (VAEs), a major class of DGMs, reveals severe problems in their uncertainty representations. Here we draw inspiration from classical computer vision to introduce an inductive bias into the VAE by incorporating a global explaining-away latent variable, which remedies defective inference in VAEs. Unlike standard VAEs, the Explaining-Away VAE (EA-VAE) provides uncertainty estimates that align with normative requirements across a wide spectrum of perceptual tasks, including image corruption, interpolation, and out-of-distribution detection. We find that restored inference capabilities are delivered by developing a motif in the inference network (the encoder) which is widespread in biological neural networks: divisive normalization. Our results establish EA-VAEs as reliable tools to perform inference under deep generative models with appropriate estimates of uncertainty.

This talk is part of the Computational Neuroscience series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

The Old Library, Darwin College GS15, Computer Laboratory Caius College, Cambridge

Other talks

Packing the Border: Quail Crates and the Regulation of Animal Movement on the US-Mexico Border, 1910s-1940s When Programmes Disagree About Programmes: Code Poetry and the Problem of Programme–Programme Communication Tea and Coffee Break title and abstract tba (joint seminar with Spectral Geometry in the Clouds) Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge Title to be confirmed
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity