Campus Event Calendar
Event Entry
New for: D1, D2, D3, INET, D4, D5, D6
What and Who
Mechanistic interpretability of neural networks
Jonas Fischer
Max-Planck-Institut für Informatik - D2
Joint Lecture Series
AG 1, AG 2, AG 3, INET, AG 4, AG 5, D6, SWS, RG1, MMCI
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Wednesday, 6 November 2024
12:15
60 Minutes
E1 5
002
Saarbrücken
Abstract
Modern machine learning (ML) has largely been driven by neural networks, delivering outstanding results not only in traditional ML applications, but also permeating into classical sciences solving open problems in physics, chemistry, and biology. This success came at a cost, as typical neural network architectures are inherently complex and their reasoning processes opaque. In domains where insights weigh more than prediction, such as modeling of systems biology, or in high-stakes decision making, such as healthcare and finance, the reasoning process of a neural network however needs to be transparent.
Recently, the mechanistic interpretation of this reasoning process has gained significant attention, which is concerned with understanding the *internal reasoning process* of a network, including what information particular neurons respond to and how these specific neurons are organized into larger circuits. In this talk, I will (1) gently introduce the topic of mechanistic interpretability in machine learning, (2) show how to discover mechanistic circuits within a neural network, (3) discuss the relevance of mechanistic interpretability in real-world applications, and (4) discuss what is still missing in the field.
Contact
Jennifer Müller
+49 681 9325 2900
--email hidden
Virtual Meeting Details
Zoom
997 1565 5535
passcode not visible
logged in users only
Jennifer Müller, 11/15/2024 11:53
Jennifer Müller, 08/27/2024 11:26 -- Created document.
Jennifer Müller, 08/27/2024 11:26 -- Created document.