Why do varied DNN designs yield equally good models of human vision? Our preprint with Mick Bonner shows that diverse DNNs represent images with a shared set of latent dimensions, and these shared dimensions turn out to also be the most brain-aligned. arxiv.org/abs/2408.12804

Then it was the turn of Hans Op de Beeck with Andrea Costantino , Filippo Cerpelloni & Yi Joanne Lin discussing computational models in different fields and expertises.

The vocabulary of systems neuroscience may appear daunting to many. Here's a short dictionary of common terms. BTW if you use them in your papers and grants you will have greater success

Big thanks to professor Martin Schrimpf for the excellent talk on recent advances in NeuroAI in the B&C seminar series! Andrea Costantino Hans Op de Beeck KU Leuven

If the brain contains learning systems that can optimize cost functions / minimize error signals, what might those cost functions / error signals be? I don’t mean the obvious ones like next step prediction. Rather, the interesting ones that train a human to be a human. 🧵

New paper with Leon and Erin Grant! Why do we see localized receptive fields so often, even in models without sparisity regularization? We present a theory in the minimal setting from Alessandro Ingrosso and Sebastian Goldt

Unlike the brain, most ANNs lack any kind of organization of units🧠 In our paper (ICLR 2025) with mayukh09 Apurva Ratan Murty, we present TopoLoss, a simple, scalable way to add brain-like topography to AI models with minimal performance loss🧵 toponets.github.io

Now, *that* is a way to start the weekend!