Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914768331210752 |
|---|---|
| author | Yousuf, Osama Hoskins, Brian Ramu, Karthick Fream, Mitchell Borders, William A. Madhavan, Advait Daniels, Matthew W. Dienstfrey, Andrew McClelland, Jabez J. Lueker-Boden, Martin Adam, Gina C. |
| author_facet | Yousuf, Osama Hoskins, Brian Ramu, Karthick Fream, Mitchell Borders, William A. Madhavan, Advait Daniels, Matthew W. Dienstfrey, Andrew McClelland, Jabez J. Lueker-Boden, Martin Adam, Gina C. |
| contents | Artificial neural networks have advanced due to scaling dimensions, but conventional computing faces inefficiency due to the von Neumann bottleneck. In-memory computation architectures, like memristors, offer promise but face challenges due to hardware non-idealities. This work proposes and experimentally demonstrates layer ensemble averaging, a technique to map pre-trained neural network solutions from software to defective hardware crossbars of emerging memory devices and reliably attain near-software performance on inference. The approach is investigated using a custom 20,000-device hardware prototyping platform on a continual learning problem where a network must learn new tasks without catastrophically forgetting previously learned information. Results demonstrate that by trading off the number of devices required for layer mapping, layer ensemble averaging can reliably boost defective memristive network performance up to the software baseline. For the investigated problem, the average multi-task classification accuracy improves from 61 % to 72 % (< 1 % of software baseline) using the proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15621 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance Yousuf, Osama Hoskins, Brian Ramu, Karthick Fream, Mitchell Borders, William A. Madhavan, Advait Daniels, Matthew W. Dienstfrey, Andrew McClelland, Jabez J. Lueker-Boden, Martin Adam, Gina C. Emerging Technologies Hardware Architecture Machine Learning Image and Video Processing Artificial neural networks have advanced due to scaling dimensions, but conventional computing faces inefficiency due to the von Neumann bottleneck. In-memory computation architectures, like memristors, offer promise but face challenges due to hardware non-idealities. This work proposes and experimentally demonstrates layer ensemble averaging, a technique to map pre-trained neural network solutions from software to defective hardware crossbars of emerging memory devices and reliably attain near-software performance on inference. The approach is investigated using a custom 20,000-device hardware prototyping platform on a continual learning problem where a network must learn new tasks without catastrophically forgetting previously learned information. Results demonstrate that by trading off the number of devices required for layer mapping, layer ensemble averaging can reliably boost defective memristive network performance up to the software baseline. For the investigated problem, the average multi-task classification accuracy improves from 61 % to 72 % (< 1 % of software baseline) using the proposed approach. |
| title | Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance |
| topic | Emerging Technologies Hardware Architecture Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2404.15621 |