News  |    |  September 22, 2020

3 Trusted AI Toolkits Join Linux Foundation AI as Newest Incubation Projects

News article by Christina Harter.
Published on the LF AI Foundation Website.

Excerpt:

LF AI Foundation (LF AI), the organization building an ecosystem to sustain open source innovation in artificial intelligence (AI), machine learning (ML), and deep learning (DL), today is announcing 3 Trusted AI Toolkits as its latest Incubation Projects: AI Fairness 360 Toolkit, Adversarial Robustness Toolbox, and AI Explainability 360 Toolkit. All 3 toolkits were originally released and open sourced by IBM

AI Fairness 360 Toolkit

The AI Fairness 360 (AIF360) Toolkit is an open source toolkit that can help detect and mitigate unwanted bias in machine learning models and datasets. With the toolkit, developers and data scientists can easily check and mitigate for biases at multiple points along their machine learning lifecycle, using the appropriate fairness metrics for their circumstances. It provides metrics to test for biases, and algorithms to mitigate bias in datasets and models. The AI Fairness 360 interactive experience provides a gentle introduction to the concepts and capabilities. Recently, AIF360 also announced compatibility with Scikit Learn, and an interface for R users.

Adversarial Robustness 360 Toolbox

The Adversarial Robustness 360 (ART) Toolbox is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to evaluate, defend and verify Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, generation, certification, etc.).

AI Explainability 360 Toolkit

The AI Explainability 360 (AIX360) Toolkit is a comprehensive open source toolkit of diverse algorithms, code, guides, tutorials, and demos that support the interpretability and explainability of machine learning models. The AI Explainability 360 interactive experience provides a gentle introduction to the concepts and capabilities by walking through an example use case for different consumer personas. [ . . . ]