Explaining Model Decisions and Fixing Them Through Human Feedback
Explore algorithms for explaining deep network decisions, building user trust, incorporating domain knowledge, learning grounded representations, and correcting unwanted biases in AI models.
How Can You Trust Machine Learning?
Explore a framework for trustworthy AI based on Clarity, Competence, and Alignment. Learn about explainable ML, rigorous model evaluation, and aligning AI behaviors with human values.
Jacob Andreas - Natural Language Explanations of Deep Networks
Explore strategies for generating natural language explanations of deep networks, covering medical diagnosis, multiagent communication, and neuron descriptions in AI systems.
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
Explore techniques for interpreting and explaining deep learning models, focusing on LRP rules, Taylor decomposition, and properties of effective explanations in AI systems.
How Can I Explain This to You? An Empirical Study of Deep Neural Net Explanation Methods - Spring 2021
Empirical study comparing deep neural network explanation methods, examining usability, stability, and privacy risks across various visual explanation frameworks.
Textual Explanation for Self-Driving Vehicles
Explore self-driving vehicle technology through an explainable driving model, focusing on network architecture, preprocessing, and evaluation of vehicle control and explanation generation.
Production Machine Learning Monitoring: Outliers, Drift, Explainers and Statistical Performance
Dive deep into advanced ML model monitoring techniques, including outlier detection, concept drift, explainability, and performance metrics for robust production deployments.
Build High Performance MLOps With ML Monitoring and AI Explainability
Discover techniques for enhancing MLOps through ML monitoring and AI explainability. Learn to identify model failures, address operational issues, and streamline model deployment using advanced analytics.
Time Series Machine Learning for Deployment in Healthcare
Explore time series machine learning applications in healthcare, focusing on ICU data analysis, explainability tools, and real-time evaluation for improved patient outcomes.
Quality Assurance in Machine Learning: Enhancing Trust and Reliability
Explore quality assurance in machine learning, its importance, and strategies for enhancing AI trustworthiness through lessons from other disciplines and best practices in MLOps and data science.
Build High Performance MLOps With ML Monitoring and AI Explainability
Discover techniques for enhancing MLOps through ML monitoring and AI explainability. Learn to identify model failures, address operational issues, and streamline model deployment using advanced analytics.
Deploying and Managing Machine Learning Models at Scale - A Hands-On Workshop
Deploy and manage ML models at scale. Hands-on workshop covers creation, deployment, monitoring, and management using real-life scenarios. Gain practical experience with Seldon Deploy, explainers, and outlier detection.
Explainability for Transparent Conversational Information-Seeking
Explore transparent conversational information-seeking through explainability techniques, enhancing user trust and understanding in AI-driven search and recommendation systems.
Sequential Recommendation with Collaborative Explanation via Mutual Information Maximization - Lecture 1
Explore sequential recommendation with collaborative explanation, maximizing mutual information for enhanced explainability in search and recommendation systems.
Interpretability for Deep Learning: Theory, Applications and Scientific Insights
Dive into deep learning interpretability, exploring methods to enhance transparency, safety, and trustworthiness in AI deployment while uncovering scientific insights in various domains.
Making AI Systems Trustworthy Through Intuitive Design and Human Interaction
Explore key technical approaches for building trustworthy AI systems, focusing on intuitiveness, interaction, explainability, and human domain knowledge integration for more reliable and transparent artificial intelligence.
科技：如何面對快速進步的科技？ChatGPT教我的事
探討如何應對快速變化的科技時代，分享AI研究經驗和實際應用案例。強調成為科技的主人，並介紹創新打擊假新聞的方法。
Czego nie widać w technologii? - Zaufanie, ostrożność i przełomy technologiczne
Wykład o zaufaniu, ostrożności i przełomach w technologii. Mateusz Chrobok dzieli się spostrzeżeniami na temat bezpieczeństwa, sztucznej inteligencji i jej wpływu na nasze życie.
Explaining Classifiers Under Constraints
Découvrez les méthodes pour expliquer les classificateurs sous contraintes, présentées par des experts en intelligence artificielle.
FOCUS TECHNIQUE: ANITI Gems AI - Library for Machine Learning Model Explainability
Découvrez ANITI Gems ai, une librairie innovante pour expliquer les modèles de Machine Learning. Apprenez à interpréter et comprendre les décisions des algorithmes d'IA.
Robotics Seminar - Bradley Hayes - University of Colorado Boulder
Explainable AI techniques for human-robot collaboration, focusing on shared expectations, interpretable models, and safe task planning to create trustworthy autonomous teammates in various domains.