causality, prediction in neuro, ai

Notes

• Gershman’s article: causality is invariant prediction. Neuroscience going toward prediction might not give understanding. There are similar examples in interpretability.

  • https://www.thetransmitter.org/the-big-picture/trading-places-what-happens-when-neuroscience-turns-into-machine-learning-and-machine-learning-turns-into-neuroscience/?utm_source=x&utm_medium=org-social&utm_campaign=20260323-perspectives-big-picture-what-happens-when-neuroscience-turns-into-machine-learning

• Microprocessor

  • https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005268

• Shortcut learning

  • https://www.nature.com/articles/s42256-020-00257-z

• Differences / similarities in RNNs due to architectures

  • https://proceedings.neurips.cc/paper_files/paper/2019/file/5f5d472067f77b5c88f69f1bcfda1e08-Paper.pdf

• Hypothesis testing interpretability

  • https://proceedings.neurips.cc/paper_files/paper/2024/file/abccb8a90b30d45b948360ba41f5a20f-Paper-Conference.pdf

• Physicalism, computational complexity

  • https://link.springer.com/article/10.1007/s11229-023-04366-1

• Interpretability illusions

  • https://arxiv.org/pdf/2312.03656

• Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable? (Méloux et al., arXiv 2502.20914)read

  • https://arxiv.org/pdf/2502.20914

• Transcoders find interpretable LLM feature circuits (Dunefsky et al., NeurIPS 2024)read

  • https://proceedings.neurips.cc/paper_files/paper/2024/file/2b8f4db0464cc5b6e9d5e6bea4b9f308-Paper-Conference.pdf

• The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms (Davies et al., arXiv 2408.05859)read

  • https://arxiv.org/pdf/2408.05859

• Towards Automated Circuit Discovery for Mechanistic Interpretability (Conmy et al., NeurIPS 2023)readdigest

  • https://proceedings.neurips.cc/paper_files/paper/2023/file/34e1dbe95d34d7ebaf99b9bcaeb5b2be-Paper-Conference.pdf

• Keeping-eye-still mechanism

  • https://www.pnas.org/doi/full/10.1073/pnas.93.23.13339

• Lindsay and Bau article about neural system understanding

  • https://www.sciencedirect.com/science/article/pii/S1389041723000906