用神经突触可塑性思想改进优化器，提升小数据下的训练效果。
NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics
- 基于多信号可塑性机制，动态调节梯度更新。
- 在Fashion-MNIST和少样本场景中显著优于基础梯度方法。
- 无需调参即可稳定迁移至CIFAR-10，适合资源受限场景。
优化算法是现代深度学习的核心，但多数方法仅依赖局部梯度统计。我们提出NeuroPlastic，一种受神经生物学多因子突触可塑性启发的可塑性调制优化器。该方法通过融合梯度、活动和记忆类统计的交互组件，动态调节梯度更新，形成轻量级调制层，兼容标准深度学习训练流程。在图像分类基准测试中，NeuroPlastic始终优于仅使用梯度的对照组，在Fashion-MNIST和低数据环境下提升更明显。在使用ResNet-18的CIFAR-10迁移实验中，该方法无需重调参即保持稳定且具有竞争力。结果表明，多信号可塑性启发的调制可作为传统梯度优化的有效扩展，尤其在信号有限或噪声较大的情况下，为深度学习中的梯度方法提供了新方向。
原文摘要 · Abstract (English)
Optimization algorithms are fundamental to modern deep learning, yet most widely used methods rely on update rules based primarily on local gradient statistics. We introduce NeuroPlastic, a plasticity-modulated optimizer that augments gradient-based updates with an adaptive multi-signal modulation mechanism inspired by multi-factor synaptic plasticity, a concept from neurobiology. NeuroPlastic dynamically scales gradient updates using interacting components that capture gradient, activity-like, and memory-like statistics, forming a lightweight modulation layer compatible with standard deep learning training pipelines. Across image classification benchmarks, NeuroPlastic consistently improves over a controlled gradient-only ablation, with more pronounced gains on the Fashion-MNIST benchmark and in reduced-data regimes. In transfer experiments on CIFAR-10 with ResNet-18, the method remains stable and competitive without retuning. These results suggest that multi-signal plasticity-inspired modulation can provide a useful extension to conventional gradient-driven optimization, particularly when learning signals are limited or noisy, and offer a promising direction for gradient-based methods in deep learning.
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。