# On neuroscience foundation models - with Andreas Tolias - #24 Page: https://stenobird.com/podcast/theoretical-neuroscience-podcast-6657149/on-neuroscience-foundation-models-with-andreas-tolias-24 Text version: https://stenobird.com/podcast/theoretical-neuroscience-podcast-6657149/on-neuroscience-foundation-models-with-andreas-tolias-24.md Podcast: [Theoretical Neuroscience Podcast](https://stenobird.com/podcast/theoretical-neuroscience-podcast-6657149) Published: 2025-02-01T06:00:00+00:00 Episode link: https://431c9cd0-a1ff-4f9a-ac41-4fca68240d88.libsyn.com/on-neuroscience-foundation-models-with-andreas-tolias-24 Audio file: https://traffic.libsyn.com/secure/431c9cd0-a1ff-4f9a-ac41-4fca68240d88/ThN-024-AndreasTolias_mixdown.mp3?dest-id=4181327 Processing state: not_requested JSON: https://stenobird.com/v1/public/podcasts/theoretical-neuroscience-podcast-6657149/episodes/on-neuroscience-foundation-models-with-andreas-tolias-24 Duration seconds: 5503 ## Resource The term "foundation model" refers to machine learning models that are trained on vast datasets and can be applied to a wide range of situations. The large language model GPT-4 is an example. The group of the guest has recently presented a foundation model for optophysiological responses in mouse visual cortex trained on recordings from 135.000 neurons in mice watching movies. We discuss the design, validation, use of this and future neuroscience foundation models. ## Actions - request_transcript: `POST https://stenobird.com/v1/public/podcasts/theoretical-neuroscience-podcast-6657149/episodes/on-neuroscience-foundation-models-with-andreas-tolias-24/transcription-requests` — Idempotently request low-priority transcript generation for this episode. - read_markdown: `GET https://stenobird.com/podcast/theoretical-neuroscience-podcast-6657149/on-neuroscience-foundation-models-with-andreas-tolias-24.md` — Read the agent-friendly Markdown representation of this episode resource. A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed. ## Transcript Full transcripts are not published on public pages unless there is a clear rights basis.