Open in app

Sign In

Write

Sign In

Daniel Ho
Daniel Ho

79 Followers

Home

About

Published in

Towards Data Science

·Jun 7, 2019

1000x Faster Data Augmentation

Efficiently learn data augmentation policies to improve neural network performance. — In this blog post we introduce Population Based Augmentation (PBA), an algorithm that quickly and efficiently learns a state-of-the-art approach to augmenting data for neural network training. PBA matches the previous best result on CIFAR and SVHN but uses one thousand times less compute, enabling researchers and practitioners to effectively…

Machine Learning

5 min read

1000x Faster Data Augmentation
1000x Faster Data Augmentation
Machine Learning

5 min read

Daniel Ho

Daniel Ho

79 Followers

Software Engineer working on robotics and machine learning at (Google) X. Formerly with Berkeley AI Research, NVIDIA, LLNL. Berkeley ’18.

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech

Teams