Injecting fairness into machine-learning models | MIT

Pdusit/Shutterstock

MIT researchers have found that machine-learning models that are popular for image recognition tasks actually encode bias when trained on unbalanced data. The solution they developed not only leads to models that make more balanced predictions, but also improves their performance on downstream tasks like facial recognition and animal species classification. 

Source: https://news.mit.edu/2022/unbias-machine-learning-0301 

RELATED ARTICLES

Subscribe to our newsletter