University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Generative models for few-shot prediction 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

Generative models for few-shot prediction tasks

Download to your calendar using vCal

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

Few-shot density estimation lies at the core of current meta-learning (or ‘learning to learn’) research and is crucial for intelligent systems to be able to adapt quickly to unseen tasks. In this talk we will introduce generative query networks (GQN – published in Science last year), a generative model for few-shot scene understanding that learns to capture the main features of synthetic 3D scenes. In the second half of the talk we will cover neural processes (NPs), a generalisation of the GQN training regime a wider range of tasks like regression and classification. NPs are inspired by the flexibility of stochastic processes such as Gaussian processes, but are structured as neural networks and trained via gradient descent. We show how NPs make accurate predictions after observing only a handful of training data points, yet scale to complex functions and large datasets.

This talk is part of the Machine Learning Reading Group @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

GR04, English Faculty, 9 West Road (Sidgwick Site) Average on Saturdays: 7582.82236842 kWh Dept of Experiental Psychology

Other talks

Non-stationarity in structural dynamics, challenges and implications for modelling and structural health monitoring Talk TBC Title abstract tbc Fun experiments you can only do with frogs TBC CSAR lecture: Climate Repair (TBC)
 

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