The Information Bottleneck EP7: AI and Neuroscience with Aran Nayebi
Sep 29, 2025
In this discussion, Aran Nayebi, an Assistant Professor at Carnegie Mellon University specializing in computational neuroscience and AI, shares his insights on blending machine learning with brain science. He explores the evolution of neural networks and intrinsic motivation's role in AI development. The conversation dives into the nuances of cross-species modeling, the importance of lifelong learning, and how better brain-machine interfaces can be achieved through individualized data. Nayebi's fascinating zebrafish experiments reveal connections between model objectives and neural circuits.
AI Snips
Chapters
Transcript
Episode notes
Reduce Noise In Conference Submissions
- Reduce submissions or improve reviewer incentives to boost peer-review quality at major conferences.
- Options include submission limits, review quotas tied to submissions, or submission fees to lower noise.
Adopt Rolling Or Journal-Like Reviews
- Consider journal-style or open rolling-review tracks (like TMLR) to improve review quality and engagement.
- Use longer review windows and author-reviewer interaction to make reviews more constructive.
Use Models To Test Brain Hypotheses
- Use engineering to test neuroscience hypotheses by training agents on brain-like goals and comparing internals to neural data.
- Optimizing for ethologically relevant tasks can reveal substrate-independent principles shared by brains and models.