Resources
Support your learning through our searchable research library and discover valuable resources about many topics in artificial intelligence and data analytics, such as AI ethics, bias and data tools.
Select the We Count at Large tag to view a selection of speaking engagements and presentations by IDRC team members. Many of these resources showcase the efforts of IDRC Director Jutta Treviranus, whose pioneering work and insights in AI and inclusive AI continue to inspire and lead the field.
Executive Order 13960: Promoting the Use of Trustworthy Artificial Intelligence in the Federal Government
The text of Presidential Document Executive Order 13960.
Explainability and Auditability in ML: Definitions, Techniques, and Tools
- Intermediate
This blog explores explainability and gives an overview of explainability techniques.
Explainability Won’t Save AI
- Intermediate
This piece argues that AI will continue to serve the interest of power brokers unless clear effort is made to establish the purpose of explainability for the various communities that are impacted by its use. The more stakeholders are involved, the better and more reliable AI will be in practicality.
Explainable AI: From Black Box to Glass Box
- Expert
The article differentiates between interpretable AI models and black-box deep-learning models and explores ways to turn black-box models into glass-box models and discusses how it can aid in the marketing of AI.
Explainable AI: Opening the Black Box or Pandora's Box?
- Expert
The aim of opening the black box of machine learning, which is what Explainable AI is all about, might result in opening the proverbial Pandora's box and thus undermine trust in the organization.
Explainable AI: What Is It? How Does It Work? And What Role Does Data Play?
- Intermediate
This article focuses on the principles of explainable AI as defined by the US National Institute of Standards (NIST), the types of explanation and how explainable AI works.
Explainable Artificial Intelligence: An Analytical Review
- Expert
This paper does an analysis of recent trends in explainable AI along with the Caltech-101 benchmarking dataset.
Explainable Artificial Intelligence: Exploring XAI Techniques in Military Deep Learning Applications
- Expert
The objective of this report is to present representative explainable AI techniques that have been developed in the context of deep learning.
Explainable Machine Learning in Deployment
- Expert
A study that analyzes the limits of current explainable machine learning techniques for end users and proposes a framework for establishing clear guidelines for explainability.
Explaining the Explainable AI: A 2-Stage Approach
- Intermediate
The writer contends that explainability assumes a two-step process. The first of which tries to grasp what is going on in the model while the other part is concerned with breaking down the information so that it can be digested.