Search Results - "Bayrooti, Jasmine"

Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling by Bayrooti, Jasmine, Ek, Carl Henrik, Prorok, Amanda

“…Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring…”
Get full text

Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus by Bayrooti, Jasmine, Gao, Zhan, Prorok, Amanda

“…Cooperative decentralized learning relies on direct information exchange between communicating agents, each with access to locally available datasets. The goal…”
Get full text

Multispectral Contrastive Learning with Viewmaker Networks by Bayrooti, Jasmine, Goodman, Noah, Tamkin, Alex

“…Contrastive learning methods have been applied to a range of domains and modalities by training models to identify similar "views" of data points. However,…”
Get full text

Multispectral Contrastive Learning with Viewmaker Networks by Bayrooti, Jasmine, Goodman, Noah, Tamkin, Alex

“…Contrastive learning methods have been applied to a range of domains and modalities by training models to identify similar "views" of data points. However,…”
Get full text

Reading Between the Demographic Lines: Resolving Sources of Bias in Toxicity Classifiers by Reichert, Elizabeth, Qiu, Helen, Bayrooti, Jasmine

“…The censorship of toxic comments is often left to the judgment of imperfect models. Perspective API, a creation of Google technology incubator Jigsaw, is…”
Get full text

Keep Your AI-es on the Road: Tackling Distracted Driver Detection with Convolutional Neural Networks and Targeted Data Augmentation by Mofid, Nikka, Bayrooti, Jasmine, Ravi, Shreya

“…According to the World Health Organization, distracted driving is one of the leading cause of motor accidents and deaths in the world. In our study, we tackle…”
Get full text

Temperature as Uncertainty in Contrastive Learning by Zhang, Oliver, Wu, Mike, Bayrooti, Jasmine, Goodman, Noah

“…Contrastive learning has demonstrated great capability to learn representations without annotations, even outperforming supervised baselines. However, it still…”
Get full text