Getting aligned on representational alignment

• Published in: arXiv.org
• Main Authors: Sucholutsky, Ilia, Muttenthaler, Lukas, Weller, Adrian, Peng, Andi, Bobu, Andreea, Been, Kim, Love, Bradley C, Grant, Erin, Groen, Iris, Achterberg, Jascha, Tenenbaum, Joshua B, Collins, Katherine M, Hermann, Katherine L, Oktar, Kerem, Greff, Klaus, Hebart, Martin N, Jacoby, Nori, Zhang, Qiuyi, Marjieh, Raja, Geirhos, Robert, Chen, Sherol, Kornblith, Simon, Rane, Sunayana, Konkle, Talia, O'Connell, Thomas P, Unterthiner, Thomas, Lampinen, Andrew K, Klaus-Robert Müller, Toneva, Mariya, Griffiths, Thomas L
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 02.11.2023
• Subjects: Alignment; Data processing; Information processing; Knowledge management; Machine learning; Neurosciences; Representations

Biological and artificial information processing systems form representations that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the extent to which the representations formed by these diverse systems agree? Do similarities in representations then transla...