Interpretations are useful: penalizing explanations to align neural
networks with prior knowledge

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge

30 September 2019

W. James Murdoch

Papers citing "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge"

8 / 58 papers shown

Title
Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers Hanjie Chen Yangfeng Ji AAML VLM 15 63 0 01 Oct 2020
Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach Nicholas F Halliwell Freddy Lecue FAtt 25 9 0 29 Sep 2020
Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation L. Guan Mudit Verma Sihang Guo Ruohan Zhang Subbarao Kambhampati 43 42 0 26 Jun 2020
Contextualizing Hate Speech Classifiers with Post-hoc Explanation Brendan Kennedy Xisen Jin Aida Mostafazadeh Davani Morteza Dehghani Xiang Ren 16 138 0 05 May 2020
Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence S. Raschka Joshua Patterson Corey J. Nolet AI4CE 24 484 0 12 Feb 2020
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI Alejandro Barredo Arrieta Natalia Díaz Rodríguez Javier Del Ser Adrien Bennetot Siham Tabik ... S. Gil-Lopez Daniel Molina Richard Benjamins Raja Chatila Francisco Herrera XAI 39 6,119 0 22 Oct 2019
Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems Laura von Rueden S. Mayer Katharina Beckh B. Georgiev Sven Giesselbach ... Rajkumar Ramamurthy Michal Walczak Jochen Garcke Christian Bauckhage Jannis Schuecker 39 626 0 29 Mar 2019
Regularizing Black-box Models for Improved Interpretability Gregory Plumb Maruan Al-Shedivat Ángel Alexander Cabrera Adam Perer Eric Xing Ameet Talwalkar AAML 24 79 0 18 Feb 2019