Neural networks are increasingly studied not merely as predictive systems, but as complex systems whose internal computations are themselves objects of scientific inquiry. Recent progress in mechanistic interpretability (MI) has made it possible to identify neurons, features, circuits, population structures, and dynami...
Zhi-Min Hu, Cheng-Xin Jiang, Han-Bo Xie et al.· 0 citations
Face recognition ability varies enormously across humans. Individuals with face-blindness (prosopagnosia) struggle to recognize even close family members while super-recognizers can identify strangers with exceptional accuracy. Where do ANNs fall within the human face recognition spectrum? Here, we administered the sta...
Kushal Dudipala, Florencia Martinez-Addiego, D. Rahnev et al.· bioRxiv· 0 citations
A principled zero-shot model evaluation framework in which ANN-based encoding models are frozen before being tested on not just held out images but entirely new datasets to help better understand what current models capture and what still remains to be explained.
Ruo-Lin Wang, Mayukh Deb, Alex Abate et al.· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.