Han Zhao

 

 

Han Zhao

 

 

 

 

Talk: Neural Probabilistic Circuits: Towards Compositional and Interpretable Predictions through Logical Reasoning 

End-to-end deep neural networks have achieved remarkable success across various domains but are often criticized for their lack of interpretability. While post-hoc explanation methods attempt to address this issue, they often fail to accurately represent these black-box models, resulting in misleading or incomplete explanations. To overcome these challenges, we propose an inherently transparent model architecture called Neural Probabilistic Circuits (NPCs), which enable compositional and interpretable predictions through logical reasoning. In particular, an NPC consists of two modules: an attribute recognition model, which predicts probabilities for various attributes, and a task predictor built on a probabilistic circuit, which enables logical reasoning over recognized attributes to make class predictions. In this talk, I will introduce the key components and training procedures of NPCs, as well as their compositional generalization capabilities and supports for counterfactual explanations. 

Workshop Home Page

Return to the TAU-UIUC Workshop Home Page

Home→