Weight Agnostic Neural Networks
- Not all neural network architectures are created equal, some perform much better than others for certain tasks. But how important are the weight parameters of a neural network compared to its architecture? In this work, we question to what extent neural network architectures alone, without learning any weight parameters, can encode solutions for a given task. We propose a search method for neural network architectures that can already perform a task without any explicit weight training. To evaluate these networks, we populate the connections with a single shared weight parameter sampled from a uniform random distribution, and measure the expected performance. We demonstrate that our method can find minimal neural network architectures that can perform several reinforcement learning tasks without weight training. On a supervised learning domain, we find network architectures that achieve much higher than chance accuracy on MNIST using random weights. Interactive version of this paper at https://weightagnostic.github.io/
Document Type: | Conference Object |
---|---|
Language: | English |
Author: | Adam Gaier, David Ha |
Parent Title (German): | 32nd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, 8-14 December 2019 |
First Page: | 5341 |
Last Page: | 5355 |
URL: | https://weightagnostic.github.io/ |
DOI: | https://doi.org/10.48550/arXiv.1906.04358 |
ArXiv Id: | http://arxiv.org/abs/1906.04358 |
Publisher: | Curran |
Place of publication: | Red Hook, NY |
Date of first publication: | 2019/06/11 |
Departments, institutes and facilities: | Fachbereich Informatik |
Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) | |
Dewey Decimal Classification (DDC): | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Entry in this database: | 2019/06/18 |
Licence (German): | ![]() |