Date of Award
6-1-2014
Document Type
Thesis (Undergraduate)
Department or Program
Department of Computer Science
First Advisor
Lorenzo Torresani
Abstract
In this paper, we propose to regularize deep neural nets with a new type of multitask learning where the auxiliary task is formed by agglomerating classes into super-classes. As such, it is possible to jointly train the network on the class-based classification problem AND super-class based classification problem. We study this in settings where the training set is small and show that , concurrently with a regularization scheme of randomly reinitializing weights in deeper layers, this leads to competitive results on the ImageNet and Caltech-256 datasets and state-of-the-art results on CIFAR-100.
Recommended Citation
Teterwak, Piotr, "Shared Roots: Regularizing Deep Neural Networks through Multitask Learning" (2014). Dartmouth College Undergraduate Theses. 92.
https://digitalcommons.dartmouth.edu/senior_theses/92
Comments
Originally posted in the Dartmouth College Computer Science Technical Report Series, number TR2014-762.