NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics

TL;DR

NeuroPlastic introduces a biologically inspired, multi-signal modulation optimizer that enhances gradient updates, improving deep learning performance especially in limited-data scenarios.

Contribution

It proposes a novel plasticity-inspired modulation mechanism for optimizers, integrating multiple signals to improve training stability and accuracy.

Findings

Consistently improves performance over gradient-only methods on image classification benchmarks.

Achieves more significant gains on Fashion-MNIST and in low-data regimes.

Remains stable and competitive in transfer learning experiments without retuning.

Abstract

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.