research
∙
05/03/2023
Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models
This paper aims to prove the emergence of symbolic concepts in well-trai...
share
research
∙
02/25/2023
Bayesian Neural Networks Tend to Ignore Complex and Sensitive Concepts
In this paper, we focus on mean-field variational Bayesian Neural Networ...
research
∙
11/11/2021
Towards Axiomatic, Hierarchical, and Symbolic Explanation for Deep Models
This paper proposes a hierarchical and symbolic And-Or graph (AOG) to ob...
research
∙
11/05/2021