Interpretable Function

Interpretable function research aims to create machine learning models whose decision-making processes are transparent and understandable, contrasting with the "black box" nature of many neural networks. Current efforts focus on developing novel architectures, such as those based on additive models, Laurent polynomials, or symbolic regression, and employing techniques like genetic programming and kernel regression to discover interpretable functions that approximate complex models. This pursuit is crucial for building trust in AI systems, enabling better model debugging and validation, and facilitating the application of machine learning in high-stakes domains like healthcare where understanding model behavior is paramount.

Papers

December 18, 2023

GINN-LP: A Growing Interpretable Neural Network for Discovering Multivariate Laurent Polynomial Equations
Nisal Ranasinghe, Damith Senanayake, Sachith Seneviratne, Malin Premaratne, Saman Halgamuge
Symbolic Regression Interpretable Neural Network Equation Discovery Dimensional Polynomial Interpretable Function

August 25, 2023

Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery
Patrick Emedom-Nnamdi, Timothy R. Smith, Jukka-Pekka Onnela, Junwei Lu
Reinforcement Learning Application Proficiency Prompt Recovery Action Value Function Interpretable Function

March 19, 2023

Logic of Differentiable Logics: Towards a Uniform Semantics of DL
Natalia Ślusarz, Ekaterina Komendantskaya, Matthew L. Daggitt, Robert Stewart, Kathrin Stark
Loss Function Logic Reasoning Neural Network Verification Differentiable Logic Interpretable Function

February 9, 2023

Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functions
Mahed Abroshan, Saumitra Mishra, Mohammad Mahdi Khalili
Black Box Genetic Programming Black Box Machine Learning Model Simulation Metamodeling Simple Primitive Interpretable Function

June 10, 2022

Explaining Neural Networks without Access to Training Data
Sascha Marton, Stefan Lüdtke, Christian Bartelt, Andrej Tschalzev, Heiner Stuckenschmidt
Neural Network Training Data Information Access Global Interpretability Post Hoc Interpretability Interpretable Function \Mathcal{I}$ Net

Interpretable Function

Papers

GINN-LP: A Growing Interpretable Neural Network for Discovering Multivariate Laurent Polynomial Equations

Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery

Logic of Differentiable Logics: Towards a Uniform Semantics of DL

Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functions

Explaining Neural Networks without Access to Training Data