1 code implementation • NeurIPS 2021 • Colin Conwell, David Mayo, Andrei Barbu, Michael Buice, George Alvarez, Boris Katz
Using our benchmark as an atlas, we offer preliminary answers to overarching questions about levels of analysis (e. g. do models that better predict the representations of individual neurons also predict representational similarity across neural populations?
1 code implementation • 3 Jun 2022 • Chris Hamblin, Talia Konkle, George Alvarez
Deep convolutional neural networks are a powerful model class for a range of computer vision problems, but it is difficult to interpret the image filtering process they implement, given their sheer size.
no code implementations • NeurIPS 2009 • Ed Vul, George Alvarez, Joshua B. Tenenbaum, Michael J. Black
Multiple object tracking is a task commonly used to investigate the architecture of human visual attention.
no code implementations • 15 Feb 2024 • Chris Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George Alvarez
Most research has primarily centered around attribution methods, which provide explanations in the form of heatmaps, showing where the model directs its attention for a given feature.