Nathan Helm-Burger | Bottlenecks in the Brain: how inspiration from the human connectome could improve AI interpretability.
Foresight Institute’s Neurotech Group
Bottlenecks in the Brain: how inspiration from the human connectome could improve AI interpretability.
Bio: Nathan studied neuroscience in graduate school, then spent five years working in industry as a data scientist and machine learning engineer. He has spent the last four years studying AI alignment and safety. His research topics have been: AI capability forecasting, AI Biorisk Evaluation, Corrigibility, and how we can learn from neuroscience to improve AI interpretability.
Abstract: Recent data from the Human Connectome Project has revealed surprisingly narrow informational bottlenecks. The emerging picture of a modular structure with a mix of highly dynamic boundaries and static bottlenecks. This compute graph suggests a new architecture for machine learning models with greatly improved functional localization. If the new architecture proves competitive with existing models, the functional localization would greatly improve interpretability and steerability of the resulting models.
This seminar is part of Foresight's Neurotech Seminar Series. To join future seminars in this program please apply here.
A group of neuroscience researchers, entrepreneurs, and allies advancing beneficial short-term and long-term neurotechnology applications.
Nominate a seminar presenter/topic
Feel free to reach out to lydia@foresight.org with any questions.