aix360

There are 0 repository under aix360 topic.

• firmai / ml-fairness-framework

  FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)

  fairness-mlfairness-aifairness-indicatorsexplainable-aixaiexplainable-mlinterpretable-machine-learningcontrastiveprototypicalaif360alibiaix360counterfactual
  Language:Jupyter Notebook 72
• Trusted-AI-Workshops

  IBMDeveloperUK / Trusted-AI-Workshops

  Introduction to trusted AI. Learn to use fairness algorithms to reduce and mitigate bias in data and models with aif360 and explain models with aix360

  ai-fairnessaif360jupyter-notebooksbias-metricsmachine-learningpythonwatson-studiodata-scienceaix360ai-explainabilityfairness-algorithmsbias-measurement
  Language:Jupyter Notebook 13

• IBMDeveloperUK / AIX360-Introduction

  Introduction to explaining data and machine learning models with aif360

  aix360explainable-mlwatson-studiojupyter-notebookspythonshaplimedata-science
  Language:Jupyter Notebook 7

• IBMDeveloperMEA / Trusted-AI-Build-Explainable-ML-Models-using-AIX360

  Imagine boarding the Titanic in 2021, and you have provided all your details as a passenger to the captain. There is are three people involved, the data scientist, captain and the passenger. Imagine the company who has built Titanic has created a machine ML model to predict the rate of survival of the passengers, in case of a disaster. The job of the data scientist is to make a model that is explainable to the passengers who are not technical, and that they get the answer about the reasons why they may not survive.

  aix360explainabilityexplainable-aiexplainable-mlibm-cloudmachine-learningmachinelearning
  Language:Jupyter Notebook 5

• gianluigilopardo / HELOC-Credit-Approval

  This notebook is ispired by the AIX360 HELOC Credit Approval Tutorial, which shows different explainability methods for a credit approval process. Here XGBoost is used for classification, achieving better accuracy than most of the models used in that notebook. Then, feature importance methods are shown, to be compared with the Data Scientist explanations methods provided in the above notebook. The first ones come directly with XGBoost and the other is based on SHAP.

  explainable-aicredit-approvalnotebookxgboostclassificationshapaix360
  Language:Jupyter Notebook 4

• ai-library-examples / aix4industries

  AI Explainability 360 Toolkit for Time-Series and Industrial Use Cases

  aiaix360artificial-intelligenceexplainabilityexplainable-aiexplainable-mlfault-detectionforecastingindustrialinterpretabilitymodel-agnostictime-seriesxaikdd2023ibm-researchibm-research-aiaix360-for-time-series-and-industrial-use-cases
  Language:TeX 1

• prasad9921 / ExplainableAI

  IBM AI explainability

  aix360datavisualizationdecision-treesexplainable-aiexploratory-data-analysisfaithfulnesslalelogistic-regressionmonotonicitysemi-automated-pipeline
  Language:Jupyter Notebook