Model Interpretability Courses and Certifications

UC Berkeley EECS

Interpretability and Model Editing in Large Language Models

Explore cutting-edge techniques in AI model interpretability and editing methods, focusing on understanding and modifying neural network behaviors with expert insights from Prof. David Bau.

• YouTube
• 1 hour 24 minutes
• On-Demand
• Free Video

Data Science Festival

Where Did My Model Go Wrong? Toolkits of Interpretability, Bias and Fairness to the Rescue

Explore techniques to identify and correct biases in machine learning models, interpret results, and ensure fair outcomes in model development and deployment.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Alan Turing Institute

Machine Learning - From Black Boxes to White Boxes - Mihaela van der Schaar

Exploring innovative approaches to make complex machine learning models interpretable and trustworthy, especially in medical applications, for diverse users including clinicians and patients.

• YouTube
• 1 hour 16 minutes
• On-Demand
• Free Video

Simons Institute

Interpretability - Now What?

Explore machine learning interpretability methods, focusing on Testing with Concept Activation Vectors (TCAV) and its applications in image prediction and medical diagnosis.

• YouTube
• 48 minutes
• On-Demand
• Free Video

Can We Talk Models into Seeing the World Differently?

Explore how language can influence visual perception in AI models, examining if verbal communication can alter how models interpret and understand visual information.

• YouTube
• 36 minutes
• On-Demand
• Free Video

Association for Computing Machinery (ACM)

LEMNA - Explaining Deep Learning Based Security Applications

Explore LEMNA, a novel technique for explaining deep learning models in security applications, addressing transparency concerns and improving interpretability for critical decisions.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Toronto Machine Learning Series (TMLS)

Interpretable Self-Explanatory Machine Learning Models

Explore interpretable machine learning models that are self-explanatory, focusing on making complex neural networks more transparent and understandable for critical applications.

• YouTube
• 32 minutes
• On-Demand
• Free Video

Toronto Machine Learning Series (TMLS)

Sensitivity and Interpretability of AI Models in Regulated Industries

Explore sensitivity analysis for AI model interpretability in regulated industries. Learn design and implementation approaches using case studies from healthcare and human activity data.

• YouTube
• 22 minutes
• On-Demand
• Free Video

MLOps World: Machine Learning in Production

5 Techniques to Increase Adoption Rates via Interpretability

Discover 5 techniques to boost ML project adoption through enhanced model interpretability, fostering trust and bridging gaps between end-users and data scientists.

• YouTube
• 33 minutes
• On-Demand
• Free Video

UC Berkeley EECS

Inside-Out Interpretability: Training Dynamics in Multi-Layer Transformer

Delve into transformer model training dynamics and interpretability, exploring multi-layer architectures and their behavior through advanced analysis techniques with Meta AI researcher Yuandong Tian.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Open Data Science

Machine Learning Explainability: From Beta Coefficients to SHAP Values

Master machine learning interpretability through beta coefficients, global and local explainability, and SHAPly values. Gain practical insights using Python for understanding AI models, from basic linear models to complex XGBOOST implementations.

• YouTube
• 33 minutes
• On-Demand
• Free Video

UofU Data Science

Evaluating Input Attribution Methods in Machine Learning - Plausibility and Comprehensiveness

Explore advanced concepts in gradient-based input attribution, from plausibility assessment to comprehensive evaluation methods like ROAR and Recursive-ROAR techniques.

• YouTube
• 37 minutes
• On-Demand
• Free Video

UofU Data Science

Gradient-Based Input Attribution Methods and Their Applications

Explore gradient-based input attribution methods, from fundamental concepts to practical applications, limitations, and advanced extensions in machine learning model interpretability.

• YouTube
• 58 minutes
• On-Demand
• Free Video

Simons Institute

Scalably Understanding AI with AI - Using AI Systems for Model Behavior Analysis

Explore advanced techniques for analyzing AI systems, from behavior elicitation to neuron description, focusing on using AI tools to understand and improve AI model behaviors and representations.

• YouTube
• 46 minutes
• On-Demand
• Free Video

Simons Institute

Building Scalable Systems for Automatically Understanding Large Language Models

Explore cutting-edge approaches to analyzing and understanding Large Language Models through scalable automated systems, focusing on cognitive science and linguistics perspectives.

• YouTube
• 36 minutes
• On-Demand
• Free Video