Structured Convolution Matrices For Energyefficient Deep Learning
ASecurity
**arXiv ID:** 1606.02407 **Authors:** Rathinakumar Appuswamy, Tapan Nayak, John Arthur, Steven Esser, Paul Merolla, Jeffrey Mckinstry, Timothy Melano, Myron Flickner, Dharmendra Modha **Published:** 2016-06-08T05:31:43Z **Abstract:** We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrice...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Structured Convolution Matrices For Energyefficient Deep Learning?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-structured-convolution-matrices-for-energyefficien)
# Structured Convolution Matrices for Energy-efficient Deep learning
**arXiv ID:** 1606.02407
**Authors:** Rathinakumar Appuswamy, Tapan Nayak, John Arthur, Steven Esser, Paul Merolla, Jeffrey Mckinstry, Timothy Melano, Myron Flickner, Dharmendra Modha
**Published:** 2016-06-08T05:31:43Z
**Abstract:**
We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrices and achieve state-of-the-art trade-off between energy efficiency and classification accuracy for well-known image recognition tasks. We also put forward a novel method to train binary convolutional networks by utilising an existing connection between noisy-rectified linear units and binary activations.
## Skill Description
This skill is generated from the arXiv paper: Structured Convolution Matrices for Energy-efficient Deep learning (1606.02407).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1606.02407](http://arxiv.org/abs/1606.02407v1)