Lei Le — accepted AI-conference papers

2019

Learning Macroscopic Brain Connectomes via Group-Sparse Factorization

Farzane Aminmansour, Andrew Patterson, Lei Le, Yisu Peng, Daniel Mitchell, Franco Pestilli +3

NeurIPS 2019poster

Mapping structural brain connectomes for living human brains typically requires expert analysis and rule-based models on diffusion-weighted magnetic resonance imaging. A data-driven approach, however, could overcome limitations in such rule-based approaches and improve precision mappings for individ…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2018

Supervised autoencoders: Improving generalization performance with unsupervised regularizers

Lei Le, Andrew Patterson, Martha White

NeurIPS 2018poster

Generalization performance is a central goal in machine learning, particularly when learning representations with large neural networks. A common strategy to improve generalization has been through the use of regularizers, typically as a norm constraining the parameters. Regularizing hidden layers i…

Cited by 332 Source ↗PDF ↗Scholar ↗