all AI news
Explaining Explainability: Understanding Concept Activation Vectors
April 8, 2024, 4:42 a.m. | Angus Nicolson, Lisa Schut, J. Alison Noble, Yarin Gal
cs.LG updates on arXiv.org arxiv.org
Abstract: Recent interpretability methods propose using concept-based explanations to translate the internal representations of deep learning models into a language that humans are familiar with: concepts. This requires understanding which concepts are present in the representation space of a neural network. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are learnt using a probe dataset of concept exemplars. In this work, we investigate three properties of CAVs. CAVs may be: (1) inconsistent …
abstract arxiv concept concepts cs.ai cs.cv cs.hc cs.lg deep learning explainability humans interpretability language network neural network popular representation space translate type understanding vectors
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Robotics Technician - 3rd Shift
@ GXO Logistics | Perris, CA, US, 92571