Stephen Hahn, Rico Zhu, Simon Mak, Cynthia Rudin, and Yue Jiang. 2023. An Interpretable, Flexible, and Interactive Probabilistic Framework for Melody Generation. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '23). Association for Computing Machinery, New York, NY, USA, 4089–4099. https://doi.org/10.1145/3580305.3599772 | I love #interpretableAI and generally the kinda stuff Cynthia rudin produces. Made a few tunes using the tool and they are pretty damn good

“Why is it that neurons sometimes align with features and sometimes don't? Why do some models and tasks have many of these clean neurons, while they're vanishingly rare in others?

In this paper, we use toy models — small ReLU networks trained on synthetic data with sparse input features — to investigate how and when models represent more features than they have dimensions.“

https://transformer-circuits.pub/2022/toy_model/index.html

#AnthropicAI #InterpretableAI #superposition

RT @james_y_zou
Excited to present SkinCon at #NeurIPS2022!

We curated a dataset of >3800 skin disease images. Each densely annotated by dermatologists w/ 48 concepts.

🪙⛽️ for #interpretableAI R&D, improving medical #AI + more.

Paper: https://openreview.net/pdf?id=gud0qopqJc4
Data: https://skincon-dataset.github.io/

RT @james_y_zou@twitter.com

Excited to present SkinCon at #NeurIPS2022!

We curated a dataset of >3800 skin disease images. Each densely annotated by dermatologists w/ 48 concepts.

🪙⛽️ for #interpretableAI R&D, improving medical #AI + more.

Paper: https://openreview.net/pdf?id=gud0qopqJc4
Data: https://skincon-dataset.github.io/

🐦🔗: https://twitter.com/james_y_zou/status/1592531662327648258