[PhilPhys] Rescheduled for 1/22 - John Morrison - Do neural networks understand what they are doing?
Center for Phil Sci
center4philsci at gmail.com
Fri Nov 20 15:56:20 CET 2026
The Center for Philosophy of Science at the University of Pittsburgh
invites you to join us for our 67th Annual Lecture Series Talk. Attend in
person in room 1008 in the Cathedral of Learning (10th Floor) or visit our
live stream on YouTube at
https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg.
The Annual Lecture Series, the Center’s oldest program, was established in
1960, the year when Adolf Grünbaum founded the Center. Each year the series
consists of six to eight lectures, about three quarters of which are given
by philosophers, historians, and scientists from other universities.
*Annual Lecture Series: *John Morrison -
https://barnard.edu/profiles/john-morrison
*Friday, January 22nd @ 3:30 pm - 5:30 pm EST*
1008 Cathedral of Learning
Zoom: TBA
*Title: **Do neural networks understand what they are doing?*
Abstract:
It is often claimed that neural networks construct models of the world
(“world models”) and do not merely exploit heuristics. In this sense, they
are said to understand their tasks. But it is not always clear what having
a world model amounts to, or what should count as evidence for or
against. In the first half of the talk, I propose a minimal notion of a
world model: a single, unified representation of a task that preserves its
structural relations. I explain how this notion sits within a hierarchy of
stronger ones, and argue that many disputes about world models are merely
verbal. In the second half of the talk, I reassess the standard example of
a network using a world model: Othello-GPT, a transformer widely taken to
use a model of the Othello board. I argue that the existing evidence is
ambiguous once we adopt the right baselines and the right metrics. I then
introduce another kind of evidence that favors the heuristic
interpretation: how quickly the network learns variants of Othello that
extend rather than scramble the board’s geometry. I end by drawing general
lessons for attributing world models to neural networks, and by describing
similar approaches for attributing algorithms and probabilistic inference.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listbox.elte.hu/pipermail/philphys/attachments/20261120/237e32d6/attachment.html>
More information about the PhilPhys
mailing list