1/ Excited to share a new NeuroAI preprint: “What can 1.8 billion regressions tell us about the pressures shaping high-level visual representation in brains and machines?” Led by Colin Conwell, with @_jacobprince_, @cvnlab, and @grez72. biorxiv.org/content/10.110…2/ Rapid progress in computer vision is producing an abundance of open-source models, which vary in their architectures, learning objectives, and input diets. But which of these factors are most important for learning brain-aligned representations?
Jun 20, 2020 • 20 tweets • 16 min read
Proud to highlight the hard work of this amazing team of researchers in the Harvard Vision Sciences Lab! #VSS2020. 1/n@fenildoshi009 explores how to link neurophysiology to perceptual psychology using deep neural networks. Poster:rb.gy/vfo0sw Video Walkthrough:rb.gy/gpmeix 2/n