List: IML | Curated by Conor O'Sullivan

Nov 27, 2023
15 stories
IML
In
TDS Archive
by
Rodrigo Silva
Exploring Feature Extraction with CNNsUsing a Convolutional Neural Network to check specialization in feature extraction
Nov 25, 2023
1
Nov 25, 2023
1
Pacmed
Explainability for tree-based models: which SHAP approximation is best?Understanding TreeSHAP algorithms’s failure modes
Jan 12, 2022
Jan 12, 2022
In
TDS Archive
by
Charu Makhijani
Explainable AI: Unfold the BlackboxBuild trust in machine learning with XAI, Guide to SHAP & SHapley Values
May 26, 2022
3
May 26, 2022
3
In
TDS Archive
by
Salih Salih
Three Interpretability Methods to Consider When Developing Your Machine Learning ModelIntroduction to SHAP, LIME, and Anchors, with examples, similarities, pros and cons.
Mar 4, 2022
1
Mar 4, 2022
1
In
TDS Archive
by
Salih Salih
Understanding Machine Learning InterpretabilityIntroduction to machine learning interpretability, driving forces, taxonomy, example, and notes on interpretability assessment.
Jan 26, 2022
2
Jan 26, 2022
2
In
TDS Archive
by
José Padarian
Explaining a CNN generated soil map with SHAPUsing SHAP to corroborate that the digital soil mapping CNN is capturing sensible relationships.
Apr 7, 2020
3
Apr 7, 2020
3
Interpretable machine learning (IML) and explainable AI (XAI)
Dr. Holger Bartel
Explainable AI Insurance RatingsInsurance is business is complex — let’s make it explainable
Jun 7, 2022
Jun 7, 2022
In
Artificial Intelligence in Plain English
by
Chau Pham
Understanding SHAP for Interpretable Machine LearningIn this post, we will get the idea of Shapley value, why the order of features matter, how to move from Shapley value to SHAP, the story…
Aug 27, 2020
3
Aug 27, 2020
3
In
Becoming Human: Artificial Intelligence Magazine
by
MobiDev
Using Explainable AI in Decision-Making ApplicationsThere is no instruction to a decision making process. However, important decisions are usually made by analyzing tons of data to find the…
Jun 13, 2022
Jun 13, 2022
In
TDS Archive
by
Noga Gershon Barak
InterpretML: Another Way to Explain Your ModelAn overview of the InterpretML package, which offers new explainability tools along side existing ones.
Nov 17, 2021
2
Nov 17, 2021
2
Dave Cote, M.Sc.
Demonstrating the power of feature engineering — Part II: How I beat XGBoost with Linear Regression!Yes, you read correctly!
Feb 8, 2022
6
Feb 8, 2022
6
In
TDS Archive
by
Vinícius Trevisan
Boruta SHAP: an amazing tool for feature selection every data scientist should knowHow we can use Boruta and SHAP to build an amazing feature selection process — with python examples
Jan 25, 2022
4
Jan 25, 2022
4
In
The Startup
by
Ula La Paris
Push the limits of explainability — an ultimate guide to SHAP libraryThis article is a guide to the advanced and lesser-known features of the python SHAP library. It is based on an example of tabular data…
Jun 5, 2020
5
Jun 5, 2020
5
In
TDS Archive
by
Aneesh Bose
Parallelize your massive SHAP computations with MLlib and PySparkA stepwise guide for efficiently explaining your models using SHAP.
May 28, 2022
5
May 28, 2022
5
Gaurav Agarwal
Explainable AI: When life gives you LIME, make mojito“I tested my ML model on the cross validation data set and it generated outstanding metrics. There is no way it will not perform well in…
Jun 5, 2022
Jun 5, 2022