About this course
Learn best practices for how to produce explainable AI and interpretable machine learning solutions.
Exploring the world of explainable AI and interpretable machine learning
1m 2sTarget audience
1m 18sWhat you should know
1m 3sUnderstanding the what and why your models predict
4m 28sVariable importance and reason codes
2m 22sComparing IML and XAI
4m 23sTrends in AI making the XAI problem more prominent
6m 18sLocal and global explanations
2m 23sXAI for debugging models
2m 26sKNIME support of global and local explanations
2m 22sChallenges of variable attribution with linear regression
8m 48sChallenges of variable attribution with neural networks
3m 30sRashomon effect
4m 42sWhat qualifies as a black box?
2m 51sWhy do we have black box models?
4m 20sWhat is the accuracy interpretability tradeoff?
4m 31sThe argument against XAI
3m 2sIntroducing KNIME
4m 8sBuilding models in KNIME
5m 13sUnderstanding looping in KNIME
3m 1sWhere to find available KNIME support for XAI
2m 53sProviding global explanations with partial dependence plots
4m 58sUsing surrogate models for global explanations
1m 52sDeveloping and interpreting a surrogate model with KNIME
4m 52sPermutation feature importance
1m 11sGlobal feature importance demo
6m 54sDeveloping an intuition for Shapley values
4m 35sIntroducing SHAP
1m 48sUsing LIME to provide local explanations for neural networks
2m 23sWhat are counterfactuals?
2m 27sKNIME's Local Explanation View node
4m 3sXAI View node demonstrating KNIME
6m 41sGeneral advice for better IML
4m 39sWhy feature engineering is critical for IML
2m 10sCORELS and recent trends
4m 59sContinuing to explore XAI
1m 21s