AAAI 2021 Tutorial on Explaining Machine Learning Predictions
AAAI 2021 Tutorial on
Explaining Machine Learning Predictions:
State-of-the-art, Challenges, and Opportunities
Himabindu Lakkaraju (Harvard)
Julius Adebayo (MIT)
Sameer Singh (UCI)
https://explainml-tutorial.github.io/
As machine learning is deployed in all aspects of society, it has become increasingly important to ensure stakeholders understand and trust these models. Decision makers must have a clear understanding of the model behavior so they can diagnose errors and potential biases in these models, and decide when and how to employ them. However, most accurate models that are deployed in practice are not interpretable, making it difficult for users to understand where the predictions are coming from, and thus, difficult to trust. Recent work on explanation techniques in machine learning offers an attractive solution: they provide intuitive explanations for “any” machine learning model by approximating complex machine learning models with simpler ones.
In this tutorial, we will discuss several post hoc explanation methods, and focus on their advantages and shortcomings. We will cover three families of techniques: (a) single instance gradient-based attribution methods (saliency maps), (b) model agnostic explanations via perturbations, such as LIME and SHAP, and (c) surrogate modeling for global interpretability, such as MUSE. For each of these approaches, we will provide their problem setup, prominent methods, example applications, and finally, discuss their vulnerabilities and shortcomings. We hope to provide a practical and insightful introduction to explainability in machine learning.
Видео AAAI 2021 Tutorial on Explaining Machine Learning Predictions канала UCI NLP
Explaining Machine Learning Predictions:
State-of-the-art, Challenges, and Opportunities
Himabindu Lakkaraju (Harvard)
Julius Adebayo (MIT)
Sameer Singh (UCI)
https://explainml-tutorial.github.io/
As machine learning is deployed in all aspects of society, it has become increasingly important to ensure stakeholders understand and trust these models. Decision makers must have a clear understanding of the model behavior so they can diagnose errors and potential biases in these models, and decide when and how to employ them. However, most accurate models that are deployed in practice are not interpretable, making it difficult for users to understand where the predictions are coming from, and thus, difficult to trust. Recent work on explanation techniques in machine learning offers an attractive solution: they provide intuitive explanations for “any” machine learning model by approximating complex machine learning models with simpler ones.
In this tutorial, we will discuss several post hoc explanation methods, and focus on their advantages and shortcomings. We will cover three families of techniques: (a) single instance gradient-based attribution methods (saliency maps), (b) model agnostic explanations via perturbations, such as LIME and SHAP, and (c) surrogate modeling for global interpretability, such as MUSE. For each of these approaches, we will provide their problem setup, prominent methods, example applications, and finally, discuss their vulnerabilities and shortcomings. We hope to provide a practical and insightful introduction to explainability in machine learning.
Видео AAAI 2021 Tutorial on Explaining Machine Learning Predictions канала UCI NLP
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
AutoPrompt: Eliciting Knowledge from Language Models w/ Automatically Generated Prompts (EMNLP 2020)¿Qué es OpenAI y su propuesta para la inteligencia artificial?AI VS ML VS DL VS Data ScienceNeurIPS 2021: Reliable Post hoc Explanations: Modeling Uncertainty in ExplainabilityEMNLP 2020 Tutorial on Interpreting Predictions of NLP ModelsCombining Feature and Instance Attribution to Detect Artifacts (ACL Findings 2022)How is artificial intelligence used in the mining industry?How I Learnt Machine Learning In 6 Steps (3 months)How to Win LMs and Influence Predictions (Sameer Singh, UCI), Repl4NLP 2021 Invited TalkNeurIPS 2020 Tutorial on Explaining ML Predictions: State-of-the-art, Challenges, and OpportunitiesCurrent Approaches in Interpretable Machine Learning with Professor Cynthia RudinYann LeCun (Facebook) - Self supervised learning and uncertainty representation,🖥️ WRITING MY FIRST MACHINE LEARNING GAME! (1/4)Hima Lakkaraju: How can we fool LIME and SHAP? Adversarial Attacks on Explanation MethodsThe 7 steps of machine learningMarco Tulio Ribeiro: “Why Should I Trust You?'”: Explaining the Predictions of Any ClassifierInterpretability vs. Explainability in Machine LearningToward Causal Machine Learning - Prof. Bernhard Schölkopf11. Introduction to Machine LearningAAAI-19 Invited Talk - Ian Goodfellow (Google AI) - Adversarial Machine Learning