Explainable AI Resources

Watch this session with George Mathew, Managing Director at Insight Partners to learn about the current state of AI, the different modalities of human and machine interaction, the advancements, and challenges AI presents.

Fiddler’s founder and CEO Krishna Gade sat down with Forward to talk about explainable AI, lessons from Microsoft, Twitter, Pinterest, Facebook, Bing vs. Google, raising $45M and what should entrepreneurs building in AI today focus on.

Krishna Gade, Founder & CEO of Fiddler, discusses how companies should care about explainability and building MLOps systems at scale.

Learn how human-centric approach to designing better frameworks and training to fully utilize the potential of explainable tools.

Learn how to perform root cause analysis to gain contextual insights, and improve model outcomes using Fiddler's analytics capabilities.

Learn how to get a deep understanding of model predictions using Fiddler's explainability capabilities.

Krishnaram Kenthapadi, Chief Scientist at Fiddler, explains the importance of validating models post-deployment and why you should test your AI early and often.

Krishna Gade, Founder & CEO of Fiddler, discusses how companies can address potential bias and other challenges in their AI.

Hima Lakkaraju, assistant professor at Harvard University, explains how to monitor the behavior of ML models through model interpretations and explanations.

Krishnaram Kenthapadi, Chief Scientist at Fiddler AI, explains the common model issues that lead to performance degradation and how to monitor ML models.

Fiddler CEO Krishna Gade sat down with the Montgomery Summit to discuss the need for model performance management and the critical role of explainability for AI solutions.

Learn about FairCanary, a novel approach to generating feature-level bias explanations that is an order of magnitude faster than previous methods.

Watch a panel discussion on the challenges and limitations of explainability for machine learning in credit underwriting models.

A panel of industry and research experts discuss the state of explainable AI today and what the future holds.

Fiddler Founder & CEO Krishna Gade discusses how explainable AI can address model bias, expedite debugging, and accelerate trust in AI-driven decision making.

Krishna Gade, Founder of Fiddler AI, discusses how to build AI responsibly, shares real-world examples, and shows why explainable AI is critical.

Hear a panel of experts shed light on the state of explainable AI, key considerations for success moving forward, and the latest research and industry trends.

Read about GroupShapley and GroupIG (Integrated Gradients), axiomatically justified methods to understand drift in ML model prediction distributions over time.

Improve your MLOps workflow on SageMaker using Fiddler's Model Performance Management platform.

Watch this panel discussion on building responsible, ethical, and accountable AI.

Learn how organizations view and use explainability for stakeholder consumption, including a framework for establishing clear goals for explainability.

Learn how subtle differences in the underlying game formulations of existing methods can cause large differences in the attributions for a prediction.

Watch this panel discussion on how to explain opaque model behavior using explainable AI.

Watch a presentation on the practical challenges and lessons learned by experts implementing explainable AI in industry.

Luke Merrick presents to the Data Council on how to put explainable AI into practice.

Learn how randomized feature ablation helps measure the importance of a feature on a model's ability to make good predictions.

An overview of model interpretability and explainability in AI, key regulations/laws, and techniques/tools for providing explainability as part of AI/ML systems