ملف الباحث
Laurens van der Maaten
ورقتان في مجموعة PaperMetrix
المنشورات
أوراق هذا المؤلف
-
Physical Reasoning Using Dynamics-Aware Models
2021 · arXiv (Cornell University)
A common approach to solving physical-reasoning tasks is to train a value learner on example tasks. A limitation of such an approach is it requires learning about object dynamics solely from reward values assigned to …
-
A Systematic Study of Bias Amplification
2022 · arXiv (Cornell University)
Recent research suggests that predictions made by machine-learning models can amplify biases present in the training data. When a model amplifies bias, it makes certain predictions at a higher rate for some groups than expected …