通过两种新方法提升液体状态机性能，显著改善神经形态识别效果。
Temporal and Spatial Reservoir Ensembling Techniques for Liquid State Machines
- 提出多尺度与时间分块集成策略，增强液体状态机表达能力。
- 在N-MNIST上达98.1%准确率，优于以往所有基于LSM的方法。
- 适合神经形态计算、脉冲神经网络研究者参考。
液态状态机（LSM）是受大脑神经元结构启发的脉冲神经网络模型，常用于神经形态视觉与语音任务。尽管表现良好，但其性能受限于固定结构，扩大网络规模虽能提升性能，却带来巨大计算开销且收益递减。本文提出两种集成技术：多长度尺度液态池集成（MuLRE）与时间激发分区液态池集成（TEPRE），并在Neuromorphic-MNIST（N-MNIST）、Spiking Heidelberg Digits（SHD）和DVSGesture三个标准神经形态数据集上进行评估。实验表明，使用3600个神经元的LSM模型，在N-MNIST上取得98.1%的测试准确率，超越所有已有基于LSM的方法；在SHD数据集上达到77.8%准确率，与使用反向传播通过时间（BPTT）训练的标准脉冲循环网络相当。此外，还引入基于感受野的输入权重设计，进一步提升视觉任务表现。本工作为提升LSM性能提供了有效扩展路径。
原文摘要 · Abstract (English)
Reservoir computing (RC), is a class of computational methods such as Echo State Networks (ESN) and Liquid State Machines (LSM) describe a generic method to perform pattern recognition and temporal analysis with any non-linear system. This is enabled by Reservoir Computing being a shallow network model with only Input, Reservoir, and Readout layers where input and reservoir weights are not learned (only the readout layer is trained). LSM is a special case of Reservoir computing inspired by the organization of neurons in the brain and generally refers to spike-based Reservoir computing approaches. LSMs have been successfully used to showcase decent performance on some neuromorphic vision and speech datasets but a common problem associated with LSMs is that since the model is more-or-less fixed, the main way to improve the performance is by scaling up the Reservoir size, but that only gives diminishing rewards despite a tremendous increase in model size and computation. In this paper, we propose two approaches for effectively ensembling LSM models - Multi-Length Scale Reservoir Ensemble (MuLRE) and Temporal Excitation Partitioned Reservoir Ensemble (TEPRE) and benchmark them on Neuromorphic-MNIST (N-MNIST), Spiking Heidelberg Digits (SHD), and DVSGesture datasets, which are standard neuromorphic benchmarks. We achieve 98.1% test accuracy on N-MNIST with a 3600-neuron LSM model which is higher than any prior LSM-based approach and 77.8% test accuracy on the SHD dataset which is on par with a standard Recurrent Spiking Neural Network trained by Backprop Through Time (BPTT). We also propose receptive field-based input weights to the Reservoir to work alongside the Multi-Length Scale Reservoir ensemble model for vision tasks. Thus, we introduce effective means of scaling up the performance of LSM models and evaluate them against relevant neuromorphic benchmarks
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。