cPNN：连续渐进神经网络用于演化流时间序列
cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series
AI总结：
cPNN通过连续渐进神经网络有效处理流时间序列中的概念漂移和时间依赖性，避免灾难性遗忘，提升模型适应性与鲁棒性。
摘要：
处理无界数据流涉及克服数据独立同分布的假设。实际上，数据流可能具有时间依赖性（即是一个时间序列），并且数据分布可能随时间变化（概念漂移）。这两个问题被深入讨论，而现有解决方案分别解决它们：缺乏联合解决方案。此外，学习多个概念意味着记住过去（即避免神经网络中的灾难性遗忘）。本文提出连续渐进神经网络（cPNN），一种能够抑制概念漂移、处理时间依赖性并绕过灾难性遗忘的解决方案。cPNN是渐进神经网络的连续版本，这是一种用于记住旧概念并快速转移过去知识以适应新概念的方法。我们的方法基于循环神经网络，并利用随机梯度下降应用于具有时间依赖性的数据流。消融研究的结果显示，cPNN能够快速适应新概念并具有对漂移的鲁棒性。
英文摘要：
Dealing with an unbounded data stream involves overcoming the assumption that data is identically distributed and independent. A data stream can, in fact, exhibit temporal dependencies (i.e., be a time series), and data can change distribution over time (concept drift). The two problems are deeply discussed, and existing solutions address them separately: a joint solution is absent. In addition, learning multiple concepts implies remembering the past (a.k.a. avoiding catastrophic forgetting in Neural Networks' terminology). This work proposes Continuous Progressive Neural Networks (cPNN), a solution that tames concept drifts, handles temporal dependencies, and bypasses catastrophic forgetting. cPNN is a continuous version of Progressive Neural Networks, a methodology for remembering old concepts and transferring past knowledge to fit the new concepts quickly. We base our method on Recurrent Neural Networks and exploit the Stochastic Gradient Descent applied to data streams with temporal dependencies. Results of an ablation study show a quick adaptation of cPNN to new concepts and robustness to drifts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
