用类脑学习机制提升音频分类的持续学习能力
Incremental learning for audio classification with Hebbian Deep Neural Networks
- 基于赫布学习原理，动态调节网络核以平衡新旧知识
- 在ESC-50数据集上达76.3%准确率，五步增量学习中更稳定
- 适合需要长期更新的音频识别场景，如智能语音系统
人类终身学习能力为深度学习，尤其是持续学习提供了灵感。本文将生物启发的赫布学习应用于声音分类任务，提出一种核可塑性方法，在增量学习过程中选择性地调节网络核：部分核用于学习新信息，其余核用于保留旧知识。在ESC-50数据集上，该方法在五个增量步骤中实现76.3%的整体准确率，优于无核可塑性的基线模型（68.7%），并表现出显著更强的任务间稳定性。
原文摘要 · Abstract (English)
The ability of humans for lifelong learning is an inspiration for deep learning methods and in particular for continual learning. In this work, we apply Hebbian learning, a biologically inspired learning process, to sound classification. We propose a kernel plasticity approach that selectively modulates network kernels during incremental learning, acting on selected kernels to learn new information and on others to retain previous knowledge. Using the ESC-50 dataset, the proposed method achieves 76.3% overall accuracy over five incremental steps, outperforming a baseline without kernel plasticity (68.7%) and demonstrating significantly greater stability across tasks.
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。