Human-Centered AI
AI systems are proliferating in everyday life, and it’s imperative to understand those systems from a human perspective. We design and investigate new forms of human-AI interactions and experiences that enhance and extend human capabilities for the good of our products, clients, and society at large.
Overview
Despite increasing levels of automation enabled by AI, the common thread to all of these systems is the human element: people are critical in the design, operation, and use of AI systems. We have a responsibility to ensure those systems operate transparently, act equitably, respect our privacy, and effectively serve people's needs.
How can we ensure that AI systems are designed responsibly and produce effective outcomes? We address this question by pursuing research projects across human-AI collaboration, responsible and human-compatible AI, as well as natural language and visual interaction systems.Learn more about human-centered AI
Our work
Goal-oriented flow assist: supporting low code data flow automation with natural language
Technical noteWhat is human-centered AI?
ExplainerIBM’s Uncertainty Quantification 360 toolkit boosts trust in AI
ReleaseNew smartphone app to navigate blind people to stand in lines with distances
ResearchPushing the boundaries of human-AI interaction at IUI 2021
NewsIBM FactSheets Further Advances Trust in AI
Release
Publications
- 2022
- NeurIPS 2022
- 2022
- ML4H 2022
- 2022
- NeurIPS 2022
- 2022
- CSCW 2022
- 2022
- VIS 2022
- 2022
- VIS 2022
Tools + code
AI Explainability 360
This open source toolkit contains eight algorithms that help you comprehend how machine-learning models predict labels throughout the AI application lifecycle. It’s designed to translate algorithmic research into the real-world use cases in a range of files, such as finance, human capital management, healthcare, and education.
View project →AI FactSheets 360
Toolkit to create factsheets outlining the details about how an AI service operates, how it was trained and tested, its performance metrics, fairness and robustness checks, intended uses, maintenance, and other critical details.
View project →RXNmapper
A chemically agnostic attention-guided reaction mapper.
View project →AI Model Explorer and Editor
An interactive tool for exploring and editing machine learning models. It uses sets of generated rules in order to create a model surrogate, which can then be edited and compared.
View project →Strolling Cities
An experiment of visual poetry generated by Artificial Intelligence.
View project →Learn + Play
A collection of browser-based games that explore key concepts behind IBM's AI research.
View project →
