Read the original document by opening this link in a new tab.
Table of Contents
1. Introduction
2. Motivation and Related Work
3. Methods
Summary
This paper explores hypernetworks, an approach of using one network to generate weights for another network. Hypernetworks provide an abstraction similar to nature's relationship between genotype and phenotype. The focus is on making hypernetworks useful for deep convolutional networks and long recurrent networks. The main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on various tasks. The paper discusses the motivation, related work, and methods for implementing static and dynamic hypernetworks.