FriSem
Speaker
Atticus Geiger
Friday, January 21, 2022
Department of Psychology
Building 420 050 or Zoom - Note the max capacity in room 050 is 36 and masks are required.
Atticus Geiger, Graduate Student, Department of Linguistics, Stanford University
Title: Causal Abstraction and Computational Explanations in Artificial Intelligence
Abstract: Theories of causal abstraction are a bridge between symbolic and connectionist models of computations, allowing for formally precise accounts of when a symbolic computation is implemented by a neural network. I will present on recent work where we both (1) analyze neural networks to determine whether they implement a hypothesized symbolic computation and (2) train neural networks to implement a target symbolic computation.
Contact Email
liyuxuan [at] stanford.edu
Event Link