Sign in

Danica Sutherland

@djsutherland.ml
1.1K followers 728 following 21 posts

machine learning asst prof at @cs.ubc.ca and amii statistical testing, kernels, learning theory, graphs, active learning… she/her, 🏳️‍⚧️, @queerinai.com

PostsRepliesMedia
Danica Sutherland @djsutherland.ml · 28/04/2025
AI Scientist making the funniest possible citation mistake (Goodfellow instead of Schmidhuber)
Screenshot of a slide:
AI Scientists still suffer from hallucinations

“We use an LSTM-based neural network (Goodfellow et al. 2016)” is highlighted, with the comment “Should be Hochreiter and Scmidhuber”
060
Danica Sutherland @djsutherland.ml · 22/11/2024
I used the same note recently – it’s a good note!
Screenshot from the linked paper, showing Proposition 4 which relates HSIC to the mutual information. The proof is based on Pjnsker’s inequality and the Bretagnolle-Hiber bound, with a pointer to Canonne (2023).
120
Danica Sutherland @djsutherland.ml · 22/11/2024
Well, I don’t know what else I was expecting.
Cloud of words in various colors and sizes based on a Google Scholar profile. The words “learning” and “kernel” are enormous. The next-biggest (much smaller) words include: active, deep, neural, regularization, tangent, testing, via, distribution, estimators, features, machine, mmd, model, models, regression, theory, using, approximation, case, clusters, community-led, compositional, convergence, data, differentially, distributions, dynamical, dynamics.
140