The reading group discusses (mostly recent) papers about machine learning models and algorithms that aim to learn structured, compressed and/or interpretable latent representations of observations, often with implications not only for ML problems such as machine vision or natural language processing, but also neuroscience and cognitive science.
The group is open for anyone, but operates under the assumption that participants know the basic tenets of unsupervised learning and probability theory and have read the paper assigned for the meeting.
Events of the group are advertised on a mailing list. If you wish to be on this list or have any inquiries about the series, contact Mihály Bányai.
Choosing papers for future meetings is organised in a spreadsheet, feel free to add suggestions and vote for existing ones any time.
Upcoming meeting:
Paper to be discussed: Deleu, T., Góis, A., Emezue, C., Rankawat, M., Lacoste-Julien, S., Bauer, S., & Bengio, Y. (2022, August). Bayesian structure learning with generative flow networks. In Uncertainty in Artificial Intelligence (pp. 518-528). PMLR.
Time: 17:00, November 16., 2023.
Location: CEU, 1051 Budapest, Nádor u. 15, Room 202.
Zoom link will be sent around on the mailing list a couple of days ahead, if missed it ask Mihály Bányai.