The reading group discusses (mostly recent) papers about theoretical machine learning and algorithms that aim to learn structured, compressed and/or interpretable latent representations of observations in a principled way, often with implications not only for machine learning, 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.
Upcoming meeting:
Papers to be discussed:
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020). Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456.
and
Kadkhodaie, Z., & Simoncelli, E. (2021). Stochastic solutions for linear inverse problems using the prior implicit in a denoiser. Advances in Neural Information Processing Systems, 34, 13242-13254.
Time: 17:00, Wednesday,17 April 2024.
Location: CEU Budapest site (1051 Budapest, Nádor u. 15.) N15. room 104.
Zoom: Meeting ID: 958 1085 9549 Passcode: 055053
Ildikó Varga
Department Coordinator (Budapest)
Department of Cognitive Science
H-1051 Budapest
Nádor u. 15. FT room 404.
tel: +36-1 327-3000 2941