Search Results for author: Keegan Kang

Found 2 papers, 0 papers with code

Improving Sign Random Projections With Additional Information

no code implementations ICML 2018 Keegan Kang, Weipin Wong

Sign random projections (SRP) is a technique which allows the user to quickly estimate the angular similarity and inner products between data.

Feature Representation in Convolutional Neural Networks

no code implementations8 Jul 2015 Ben Athiwaratkun, Keegan Kang

Our results show that CNN feature maps can be used with Random Forests and SVM to yield classification results that outperforms the original CNN.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.