[PhilPhys] 11/13- John Morrison - Do neural networks understand what they are doing?
Center for Phil Sci
center4philsci at gmail.com
Thu Nov 12 21:25:54 CET 2026
The Center for Philosophy of Science invites you to join us for
a Sixty-Seventh Annual Lecture Series presentation. Attend in person, Room
1008 on the 10th floor of the Cathedral of Learning 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, November 13th @ 3:30 pm - 5:30 pm EST*
Zoom: https://pitt.zoom.us/j/98388637045
*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.
This talk will be available online:
Zoom: https://pitt.zoom.us/j/98388637045
YouTube: https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listbox.elte.hu/pipermail/philphys/attachments/20261112/4cf9e939/attachment.html>
More information about the PhilPhys
mailing list