Interpretability
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
·3184 words·15 mins·
loading
·
loading
AI Theory
Interpretability
🏢 Dept. of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty, Heidelberg University, Germany
Almost-linear RNNs (AL-RNNs) offer highly interpretable symbolic codes for dynamical systems reconstruction, simplifying the analysis of complex systems.
A theoretical design of concept sets: improving the predictability of concept bottleneck models
·1648 words·8 mins·
loading
·
loading
AI Theory
Interpretability
🏢 University of Cambridge
Boosting concept bottleneck model predictability, this paper introduces a theoretical framework linking concept set properties to model performance, proposing a method for effective concept identifica…
2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
·2147 words·11 mins·
loading
·
loading
AI Theory
Interpretability
🏢 University of Illinois Urbana-Champaign
2D-OOB: a novel framework for jointly attributing data values to individual features, enabling fine-grained outlier detection and improved model performance.