用变化敏感神经元构建新型存贮计算系统，节能且性能接近传统方法。
Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators
- 用对输入变化敏感的神经元环构成小世界网络作为存贮器
- 在MNIST任务中达到90.65%准确率，与现有方法相当
- 适合低功耗AI应用，为高能耗AI提供可持续替代方案
存贮计算是一种利用复杂系统动态进行函数逼近的机器学习方法。现有方法依赖耦合积分神经元网络，需持续电流维持活性。本文提出一种由对变化敏感的神经元构成的小世界图网络，作为存贮计算的替代基底。该网络仅在输入变化时激活，无需持续电流。我们确定了使此类小世界网络有效工作的耦合强度与网络拓扑。在MNIST手写数字识别任务中，该系统实现90.65%的准确率，与现有存贮计算方法表现相当。结果表明，不同步神经元可作为积分神经元的潜在替代方案，为高能耗人工智能应用提供可持续未来路径。
原文摘要 · Abstract (English)
Reservoir Computing is a machine learning approach that uses the rich repertoire of complex system dynamics for function approximation. Current approaches to reservoir computing use a network of coupled integrating neurons that require a steady current to maintain activity. Here, we introduce a small world graph of differentiating neurons that are active only when there are changes in input as an alternative to integrating neurons as a reservoir computing substrate. We find the coupling strength and network topology that enable these small world networks to function as an effective reservoir. We demonstrate the efficacy of these networks in the MNIST digit recognition task, achieving comparable performance of 90.65% to existing reservoir computing approaches. The findings suggest that differentiating neurons can be a potential alternative to integrating neurons and can provide a sustainable future alternative for power-hungry AI applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。