用于时间序列预测与异常检测的单状态更新预测编码训练
Single State Update Predictive Coding training for Time Series Forecasting and Anomaly Detection
- Ghent University（根特大学）
- imec
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对预测编码网络的顺序反向误差传播瓶颈，提出并行训练生成式与编码式两类PCN的单状态更新训练技术，将其应用于时间序列异常检测，实现了更稳定连续的在线学习。
AI中文摘要：
预测编码（Predictive Coding，PC）是一种可实现神经网络层并行更新的神经学习范式。但PC网络（PCN）的主要瓶颈在于顺序反向误差传播。为解决该问题，我们提出一种训练技术，将生成式PCN与辅助编码PCN配对，两个PCN并行训练以匹配其神经激活值，无需顺序传播。我们将该方法应用于时间序列异常检测，结果显示其可实现更稳定、连续的在线学习。
英文摘要：
Predictive Coding (PC) is a neural learning paradigm that enables parallelizable neural network layer updates. However, the main bottleneck of PC Networks (PCN) is the sequential backwards error propagation. To tackle this, we introduce a training technique that pairs a Generative PCN with a support Encoding PCN. The two PCNs are trained in parallel to match their neural activations, without sequential propagation. We apply this to time series anomaly detection and show that our approach results in more stable, continuous, online learning.
