paper-with-me

Papers

Understanding Task Representations in Neural Networks via Bayesian Ablation

2025-05-19 · Andrew Nam, Declan Campbell, Thomas Griffiths, Jonathan Cohen, Sarah-Jane Leslie

Neural networks are powerful tools for cognitive modeling due to their flexibility and emergent properties. However, interpreting their learned representations remains challenging due to their sub-symbolic semantics. In this work, we introduce a novel probabilistic framework for interpreting latent task representations in neural networks. Inspired by Bayesian inference, our approach defines a distribution over representational units to infer their causal contributions to task performance. Using ideas from information theory, we propose a suite of tools and metrics to illuminate key model properties, including representational distributedness, manifold complexity, and polysemanticity.

📄 PDF Abstract BibTeX arXiv:2505.13742

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inference

Similar Papers 제목 키워드 기반

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

2021-05-09 · Zehao Xiao, Jiayi Shen, XianTong Zhen, Ling Shao 외

Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on vari…

Bayesian InferenceDomain Generalization

Deep Bayesian Network for Visual Question Generation

2020-01-23 · Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar, Vinay P. Namboodiri

Generating natural questions from an image is a semantic task that requires using vision and language modalities to learn multimodal representations. Images can have multiple visual and language cues such as places, capt…

Natural QuestionsQuestion GenerationQuestion-Generation

Asymptotics of representation learning in finite Bayesian neural networks

2021-06-01 · NeurIPS 2021 12 · Jacob A. Zavatone-Veth, Abdulkadir Canatar, Benjamin S. Ruben, Cengiz Pehlevan

Recent works have suggested that finite Bayesian neural networks may sometimes outperform their infinite cousins because finite networks can flexibly adapt their internal representations. However, our theoretical underst…

Representation Learning

Event Temporal Relation Extraction with Bayesian Translational Model

2023-02-10 · Xingwei Tan, Gabriele Pergola, Yulan He

Existing models to extract temporal relations between events lack a principled method to incorporate external knowledge. In this study, we introduce Bayesian-Trans, a Bayesian learning-based method that models the tempor…

Bayesian InferencemodelRelationRelation Extraction+2

Ablation Studies for Novel Treatment Effect Estimation Models

2024-10-21 · Hugo Gobato Souto, Francisco Louzada

Ablation studies are essential for understanding the contribution of individual components within complex models, yet their application in nonparametric treatment effect estimation remains limited. This paper emphasizes …

Uncertainty Quantification