February 1, 2018
Prof. Olga Russakovsky and Prof. Arvind Narayanan receive the Yang family SEAS Innovation Research Grant to study Societal Bias in Artificial Intelligence
The Princeton School of Engineering and Applied Science is able to offer grants to faculty for innovative research in areas such as general engineering, health, environment, neuroscience, and machine learning with the generosity of Princeton’s alumni, parents, and other donors.
One of the grants offered this year was to Prof. Russakovsky and Prof. Narayanan towards their collaborative research on recognizing, understanding and mitigating societal bias in Artificial Intelligence.
Artificial Intelligence (AI) technologies mediate our interactions with the world and our daily decision making, ranging from shopping to hiring to surveillance. The development of rich AI algorithms able to process and learn from unparallelled amounts of data holds promise for making impartial, well-informed decisions. However, such systems also absorb human biases, such as gender or race stereotyping. Left unchecked, they will perpetuate these biases on an unparallelled scale. One example of this can be seen in an earlier Princeton paper, coauthored by Prof. Narayanan, on how AI systems for natural language processing can reinforce harmful stereotypes.
This grant allows the beginning of a collaboration to develop the science of AI bias. The aim is to gain a deeper understanding of the problem, and to begin developing the tools and techniques for recognizing, understanding and mitigating societal bias in AI. The collaboration brings together the PIs’ expertise on information privacy and security with computer vision and deep learning.