NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics
For deep learning practitioners, this offers a lightweight, biologically inspired optimizer that enhances performance in data-limited scenarios, though gains are incremental.
NeuroPlastic introduces a plasticity-modulated optimizer that improves gradient-based updates via multi-signal modulation, achieving consistent gains over gradient-only baselines, especially on Fashion-MNIST and in low-data regimes.
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.