research
∙
06/07/2023
Don't trust your eyes: on the (un)reliability of feature visualizations
How do neural networks extract patterns from pixels? Feature visualizati...
share
research
∙
05/29/2023
Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Understanding which concepts models can and cannot represent has been fu...
research
∙
05/24/2023
Model evaluation for extreme risks
Current approaches to building general-purpose AI systems tend to produc...
research
∙
01/10/2023
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Language models are known to learn a great quantity of factual informati...
research
∙
12/22/2022
Impossibility Theorems for Feature Attribution
Despite a sea of interpretability methods that can produce plausible exp...
research
∙
12/13/2022
On the Relationship Between Explanation and Prediction: A Causal View
Explainability has become a central requirement for the development, dep...
research
∙
12/09/2022
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation
We investigate whether three types of post hoc model explanations–featur...
research
∙
06/17/2022
Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis
Each year, expert-level performance is attained in increasingly-complex ...
research
∙
02/25/2022
Human-Centered Concept Explanations for Neural Networks
Understanding complex machine learning models such as deep neural networ...
research
∙
01/11/2022
Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems
Intelligent decision support (IDS) systems leverage artificial intellige...
research
∙
11/17/2021
Acquisition of Chess Knowledge in AlphaZero
What is learned by sophisticated neural network agents such as AlphaZero...
research
∙
06/16/2021
Best of both worlds: local and global explanations with human-understandable concepts
Interpretability techniques aim to provide the rationale behind a model'...
research
∙
05/31/2021
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
Explaining deep learning model inferences is a promising venue for scien...
research
∙
11/10/2020
Debugging Tests for Model Explanations
We investigate whether post-hoc model explanations are effective for dia...
research
∙
07/09/2020
Concept Bottleneck Models
We seek to learn models that we can interact with using high-level conce...
research
∙
10/17/2019
On Concept-Based Explanations in Deep Neural Networks
Deep neural networks (DNNs) build high-level intelligence on low-level r...
research
∙
07/23/2019
BIM: Towards Quantitative Evaluation of Interpretability Methods with Ground Truth
Interpretability is rising as an important area of research in machine l...
research
∙
07/22/2019
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
Machine learning based decision making systems are increasingly affectin...
research
∙
07/16/2019
Explaining Classifiers with Causal Concept Effect (CaCE)
How can we understand classification decisions made by deep neural nets?...
research
∙
06/06/2019
Visualizing and Measuring the Geometry of BERT
Transformer architectures show significant promise for natural language ...
research
∙
03/04/2019
Do Neural Networks Show Gestalt Phenomena? An Exploration of the Law of Closure
One characteristic of human visual perception is the presence of "Gestal...
research
∙
02/08/2019
Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making
Machine learning (ML) is increasingly being used in image retrieval syst...
research
∙
02/07/2019
Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Interpretability has become an important topic of research as more machi...
research
∙
01/31/2019
An Evaluation of the Human-Interpretability of Explanation
Recent years have seen a boom in interest in machine learning systems th...
research
∙
10/23/2018
Interpreting Black Box Predictions using Fisher Kernels
Research in both machine learning and psychology suggests that salient e...
research
∙
10/08/2018
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
Explaining the output of a complicated machine learning model like a dee...
research
∙
10/08/2018
Sanity Checks for Saliency Maps
Saliency methods have emerged as a popular tool to highlight features in...
research
∙
07/03/2018
Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018)
This is the Proceedings of the 2018 ICML Workshop on Human Interpretabil...
research
∙
06/28/2018
Evaluating Feature Importance Estimates
Estimating the influence of a given feature to a model prediction is cha...
research
∙
06/22/2018
xGEMs: Generating Examplars to Explain Black-Box Models
This work proposes xGEMs or manifold guided exemplars, a framework to un...
research
∙
05/30/2018
To Trust Or Not To Trust A Classifier
Knowing when a classifier's prediction can be trusted is useful in many ...
research
∙
05/29/2018
Human-in-the-Loop Interpretability Prior
We often desire our models to be interpretable as well as accurate. Prio...
research
∙
02/02/2018
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
Recent years have seen a boom in interest in machine learning systems th...
research
∙
11/30/2017
TCAV: Relative concept importance testing with Linear Concept Activation Vectors
Neural networks commonly offer high utility but remain difficult to inte...
research
∙
11/02/2017
The (Un)reliability of saliency methods
Saliency methods aim to explain the predictions of deep neural networks....
research
∙
08/08/2017
Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)
This is the Proceedings of the 2017 ICML Workshop on Human Interpretabil...
research
∙
06/12/2017
SmoothGrad: removing noise by adding noise
Explaining the output of a deep network remains a challenge. In the case...
research
∙
05/16/2017
Learning how to explain neural networks: PatternNet and PatternAttribution
DeConvNet, Guided BackProp, LRP, were invented to better understand deep...
research
∙
02/28/2017
Towards A Rigorous Science of Interpretable Machine Learning
As machine learning systems become ubiquitous, there has been a surge of...
research
∙
07/08/2016
Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016)
This is the Proceedings of the 2016 ICML Workshop on Human Interpretabil...
research
∙
03/03/2015
The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification
We present the Bayesian Case Model (BCM), a general framework for Bayesi...
research
∙
06/05/2013
