在光学神经网络上自动化多任务学习,重量共享和物理旋转
Shanglin Zhou1, Yingjie Li2, Weilu Gao3
1School of Computing, University of Connecticut, Storrs, 06269, USA.
Scientific reports
|April 25, 2025
概括
LUMEN-PRO在微分光学神经网络 (DONN) 上实现了多任务学习 (MTL) 的自动化,提高了能源效率和精度. 这种框架显著减少了内存足迹,并提高了人工智能系统的成本效益.
科学领域:
- 人工智能的人工智能
- 光学计算是指光学计算的应用.
- 机器学习 机器学习
背景情况:
- 人工智能民主化的兴起需要高效的多任务学习 (MTL) 解决方案.
- 衍射光学神经网络 (DONN) 为MTL提供低能耗和高速度.
- 目前对MTL的DONN实现受到手动重新配置和系统重复的阻碍.
研究的目的:
- 引入LUMEN-PRO,一个使用DONNs的MTL自动化框架.
- 克服手动层重新配置和物理系统重复在基于DONN的MTL中的局限性.
- 为了提高MTL在DONNs上的能源效率,准确性和内存足迹.
主要方法:
- 开发了一个自动化的MTL框架 (LUMEN-PRO) 用于任意的骨干DONN.
- 在单个DONN架构上使用一组任务实现任务自动化.
- 利用物理光学系统的可旋转性来取代特定任务的层以旋转的共享层,优化内存.
主要成果:
- LUMEN-PRO实现了一个高精度的多任务DONN模型,其内存足迹比现有的MTL方法要小得多.
- 与单任务和现有的DONN方法相比,该框架的准确性高达49.58%,成本效益提高了4倍.
- 实现了MTL的内存下限,与单任务模型内存效率相匹配,并在每操作员效率方面超越其他系统.
结论:
- LUMEN-PRO提供了一种灵活和自动化的解决方案,用于在DONNs上节能MTL.
- 该框架显著降低了内存需求,并提高了光学AI系统的计算效率.
- 通过DONNs实现实用和高效的MTL,LUMEN-PRO代表了在实现实用和高效的MTL方面取得的重大进展.
更多相关视频
05:41A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
Published on: February 6, 2020
9.3K
07:12Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
Published on: April 11, 2025
205
相关概念视频
01:24Sequence Networks of Rotating Machines
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
01:12Observational Learning
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...