← Search

Taiga Abe

2 accepted papers

2022

Deep Ensembles Work, But Are They Necessary?

NeurIPS 2022accept

Ensembling neural networks is an effective way to increase accuracy, and can often match the performance of individual larger models. This observation poses a natural question: given the choice between a deep ensemble and a single neural network with similar accuracy, is one preferable over the othe…

2019

BehaveNet: nonlinear embedding and Bayesian neural decoding of behavioral videos

NeurIPS 2019poster

A fundamental goal of systems neuroscience is to understand the relationship between neural activity and behavior. Behavior has traditionally been characterized by low-dimensional, task-related variables such as movement speed or response times. More recently, there has been a growing interest in au…