InterpretAI
@interpret_ai
Interpreting and understanding artificial intelligence models.
ID: 1528803198252642304
http://www.interpret-ai.com 23-05-2022 18:21:39
540 Tweet
601 Followers
123 Following
The recording of my book chat on Artificial Humanities (University of Michigan Press) at UC Berkeley's Townsend Center for Humanities is now available. We discuss: the Pygmalion myth connection between Shaw's Eliza, the Turing test, and chatbots, - artificial humanities as research approach,
“Looking ahead, Beguš says he hopes to see the expansion of AI interpretability — or the ability to further analyze AI models and understand what the models are actually learning.” UC Berkeley College of Letters & Science UC Berkeley
"Terms like “subconscious,” or “deep learning,” or “embedding” strongly suggest that cognitive structures—say, brains, both organic and synthetic—have depth." — Nina Beguš, metahaven & Gašper Beguš in Latent Spacecraft
Nina Beguš metahaven Gašper Beguš "Making the latent vector navigable by mapping it onto a two-dimensional plane that we can crisscross is a straightforward way of showing that the embeddings are somewhere, and that there is thus a partially walkable interior rather than something that must remain mysteriously
