The State of Production Machine Learning in 2024
Explore challenges and best practices in production machine learning systems, covering deployment, explanation, security, monitoring, and scaling. Gain insights into the ML tooling ecosystem.
Reasons, Values, Stakeholders - A Philosophical Framework for Explainable AI
Explore a philosophical framework for explainable AI, examining the interplay between reasons, values, and stakeholders to enhance transparency and ethical considerations in artificial intelligence systems.
Explainable AI in Industry - Practical Challenges and Lessons Learned
Explore practical challenges and industry insights on implementing explainable AI, featuring expert perspectives from leading tech companies and researchers.
Impossible Explanations? Beyond Explainable AI in the GDPR from a COVID-19 Use Case Scenario
Exploring AI explainability challenges in GDPR compliance using COVID-19 scenarios, emphasizing justifiability over technical explanations in legal and ethical contexts.
Explainable AI - The Apex of Human and Machine Learning
Explore the emerging field of Explainable AI, its importance in high-risk domains, and how it bridges the gap between human cognition and machine learning for more intuitive and understandable AI systems.
Designing Theory-Driven User-Centric Explainable AI
Explore a framework for human-centered, decision-theory-driven explainable AI, bridging algorithm-generated explanations with human decision-making theories in high-stakes applications like healthcare and criminal justice.
Explainable AI Explained for Developers
Discover the importance of Explainable AI for developers, learn practical tools for interpreting machine learning models, and understand its business implications in this insightful presentation.
Automated Rationale Generation - A Technique for Explainable AI and Its Effects on Human Perceptions
Explore automated rationale generation for explainable AI, including data collection, neural network training, and user perception studies. Insights on human preferences for AI explanations.
Explainable AI Analysis Visualization - Applications from Brain Computer Interfaces to ChatGPT
Explore cutting-edge applications of explainable AI, from brain-computer interfaces to ChatGPT, with a focus on analysis and visualization techniques.
Explainable AI Analysis & Visualization - Applications from Brain Computer Interfaces to ChatGPT
Explore explainable AI analysis and visualization techniques, from brain-computer interfaces to ChatGPT, enhancing understanding of AI decision-making processes and applications.
Visualization Best Practices for Explainable AI
Explore machine learning visualization techniques for explainable AI across industries, covering model understanding, data analysis, and performance evaluation using Jupyter, Python, and Power BI.
Explainable AI with Machine Teaching
Explore the shift from Machine Learning to Machine Teaching, addressing explainability, data access, and algorithm control. Learn about transformative industry applications and real-world examples.
Explainable AI to Increase Safe Use of AI - A Case of Manufacturing
Explore how explainable AI enhances safety and transparency in manufacturing processes, focusing on practical applications and implementation strategies.
Business Value Through Explainable AI (XAI)
Discover how explainable AI frameworks enhance business value across supply chain, manufacturing, and finance through practical applications of transparent machine learning techniques.
PL4XGL: A Programming Language Approach to Explainable Graph Learning
Explore a novel programming language approach to explainable graph learning, addressing limitations in GNN explainability through a graph description language and interpretable classification model.
Trust and Loyalty of AI-Based Decisions
Explore the critical aspects of trust and loyalty in AI decision-making processes, examining their implications and challenges.
Formal XAI - Explainable Artificial Intelligence
Explore formal methods for explainable AI with Joao Marques Silva, delving into rigorous approaches for transparent and interpretable machine learning models.
Deep Learning-Based Lung Ultrasound Video Classification to Predict COVID-19
Explore deep learning methods for COVID-19 detection using lung ultrasound videos, focusing on results, methodology, and explainability of the approach.
Accelerating Model Deployment with MLOps - Google Cloud Technical Guide for Startups
Explore MLOps on Google Cloud to accelerate model deployment. Learn about challenges, solutions, and tools like Vertex Pipelines, Model Registry, and Model Monitoring through demos and customer success stories.
Technical Shortcomings of Deep Learning - Part 1
Explore technical challenges in deep learning, including data hunger, limited transfer capacity, open-ended inference, and explainability. Gain insights from Gary Marcus's critical appraisal.
Predictive ML - How Unilever is Improving its Forecasting
Unilever's reusable predictive framework improves forecasting processes using ML models, enhancing manual predictions and filling gaps for various business metrics at different granularity levels.