Model Interpretability Courses and Certifications

Machine Learning Explainability

Extract human-understandable insights from any model.

• Kaggle
• 4 hours
• Self-Paced
• Free Certificate

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Explore the "Semantic Hub Hypothesis" which proposes language models create shared representation spaces across languages and modalities, placing semantically similar inputs near each other regardless of their source type.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

MIT Deep Learning in Life Sciences Spring 2020

1 rating

Explore deep learning applications in genomics, from neural networks to single-cell analysis. Gain insights into regulatory genomics, epigenomics, and genetics through advanced computational techniques.

• YouTube
• 19 hours
• Self-Paced
• Free Video

Association for Computing Machinery (ACM)

Probing ML Models for Fairness with the What-if Tool and SHAP

Explore ML model fairness using What-if Tool and SHAP. Learn to analyze and visualize model behavior, detect biases, and understand feature importance for responsible AI development.

• YouTube
• 56 minutes
• Self-Paced
• Conference Talk

CodeEmporium

How a Data Scientist Fights Fraud - With Code!

Explore data science techniques for fraud detection, including feature engineering, SQL querying, model creation, evaluation, and interpretation, with hands-on coding examples.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Nicholas Renotte

Machine Learning Explainability & Bias Detection with Watson OpenScale

Learn to monitor, explain, and debias machine learning models using Watson OpenScale. Explore performance metrics, interpret predictions, and detect model drift for improved AI transparency and reliability.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

GOTO Conferences

Ethical ML - Who's Afraid of the Black Box Models

Explore ethical machine learning beyond interpretability, focusing on responsible data handling and fairness testing to meet GDPR and ALTAI guidelines while using black-box models.

• YouTube
• 39 minutes
• Self-Paced
• Conference Talk

GOTO Conferences

A Taste of Random Decision Forests on Apache Spark

Explore Random Decision Forests on Apache Spark with Sean Owen. Learn about decision trees, feature vectors, model interpretation, and hyperparameter tuning for machine learning in distributed environments.

• YouTube
• 53 minutes
• Self-Paced
• Conference Talk

Yannic Kilcher

Shortcut Learning in Deep Neural Networks

Explore deep neural networks' shortcut learning, its impact on AI generalization, and strategies to improve model robustness and real-world applicability.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

Data Science Dojo

Hands-on Introduction to Interpreting Machine Learning Models

Explore methods for interpreting machine learning models, including feature importance and local explanations, to increase trust in AI products and bridge gaps in problem understanding.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

EuroPython Conference

Explaining Behavior of Machine Learning Models with ELI5 Library

Explore techniques for interpreting and debugging ML models using eli5 library. Learn to explain linear models, decision trees, ensembles, and classifiers, improving trust and quality in ML solutions.

• YouTube
• 30 minutes
• Self-Paced
• Conference Talk

Toronto Machine Learning Series (TMLS)

Black-Box and Glass-Box Explanation in Machine Learning

Explore intelligibility and explanation in machine learning, comparing glass-box and black-box methods with new techniques for providing explanations.

• YouTube
• 2 hours 59 minutes
• Self-Paced
• Free Video

1littlecoder

Understanding SHAP Summary Plot - Interpretable Machine Learning - Day 19

Explore SHAP and Shapley values for interpretable machine learning, focusing on summary plots and dependence plots to enhance model explainability and insights.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Institute for Pure & Applied Mathematics (IPAM)

Machine Learning for Scientific Discovery, with Examples in Fluid Mechanics

Explore machine learning for nonlinear dynamical systems modeling, focusing on the SINDy algorithm and its applications in fluid dynamics, with emphasis on interpretable and physics-respecting solutions.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Databricks

Interpretable Machine Learning - Data Brew Season 2 Episode 7

Explore interpretable machine learning with Ameet Talwalkar, discussing its relation to data privacy, fairness, and practical applications in this insightful interview on cutting-edge ML research.

• YouTube
• 37 minutes
• Self-Paced
• Free Video