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

• URL: http://arxiv.org/abs/2604.26297v1
• Date: Wed, 29 Apr 2026 04:52:21 GMT
• Title: NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics
• Abstract summary: NeuroPlastic is a plasticity-modulated algorithm that augments gradient-based updates with an adaptive multi-signal modulation mechanism.<n>Across image classification benchmarks, NeuroPlastic consistently improves over a controlled gradient-only ablation.<n>These results suggest that multi-signal plasticity-inspired modulation can provide a useful extension to conventional gradient-driven optimization.
• Score: 9.309128231118969
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning [2.850721641556094]
  Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer.<n>We introduce Neuromodulation and Synchronization (NeuMoSync), a novel architecture that integrates dynamic, neuron-specific modulation into deep neural networks.<n>NeuMoSync extends standard neural network architectures with learnable feature vectors for each neuron that track network-wide historical context.
  arXiv  Detail & Related papers  (2026-08-05T02:01:09Z)
• Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping [66.25536973294726]
  Post-training methods for text-to-image (T2I) models are prone to reward hacking.<n>Super-Linear Advantage Shaping (SLAS) reshapes the local policy space.<n>SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T17:59:25Z)
• From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning [0.0]
  Backpropagation dominates modern machine learning, yet it is not the only principled method for optimizing dynamical systems.<n>We propose Kalman World Models (KWM), a class of learned state-space models trained via Bayesian filtering.<n>We extend this framework to transformer-based large language models (LLMs), where internal activations are treated as latent dynamical states corrected.
  arXiv  Detail & Related papers  (2026-03-13T00:30:30Z)
• Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity [0.2578242050187029]
  Control policies in deep reinforcement learning are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation.<n>This paper introduces the Self-Motivated Growing Neural Network (SMGrNN), a controller whose topology evolves online through a local Structural Plasticity Module.
  arXiv  Detail & Related papers  (2025-12-14T14:31:21Z)
• Gradient Flow Matching for Learning Update Dynamics in Neural Network Training [3.782392436834913]
  Gradient Flow Matching (GFM) is a continuous-time modeling framework that treats neural network training as a dynamical system governed by learned-aware vector fields.<n>By leveraging conditional flow matching, GFM captures the underlying update rules of SGD, Adam, and RMSprop, enabling smooth extrapolation of weight trajectories toward convergence.
  arXiv  Detail & Related papers  (2025-05-26T17:03:22Z)
• Preserving Plasticity in Continual Learning with Adaptive Linearity Injection [10.641213440191551]
  Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn.<n>Recent work has shown that deep linear networks tend to be resilient towards loss of plasticity.<n>We propose Adaptive Linearization (AdaLin), a general approach that dynamically adapts each neuron's activation function to mitigate plasticity loss.
  arXiv  Detail & Related papers  (2025-05-14T15:36:51Z)
• Contrastive Learning in Memristor-based Neuromorphic Systems [55.11642177631929]
  Spiking neural networks have become an important family of neuron-based models that sidestep many of the key limitations facing modern-day backpropagation-trained deep networks. In this work, we design and investigate a proof-of-concept instantiation of contrastive-signal-dependent plasticity (CSDP), a neuromorphic form of forward-forward-based, backpropagation-free learning.
  arXiv  Detail & Related papers  (2024-09-17T04:48:45Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Learning Large-scale Neural Fields via Context Pruned Meta-Learning [60.93679437452872]
  We introduce an efficient optimization-based meta-learning technique for large-scale neural field training. We show how gradient re-scaling at meta-test time allows the learning of extremely high-quality neural fields. Our framework is model-agnostic, intuitive, straightforward to implement, and shows significant reconstruction improvements for a wide range of signals.
  arXiv  Detail & Related papers  (2023-02-01T17:32:16Z)
• Scaling Private Deep Learning with Low-Rank and Sparse Gradients [5.14780936727027]
  We propose a framework that exploits the low-rank and sparse structure of neural networks to reduce the dimension of gradient updates. A novel strategy is utilized to sparsify the gradients, resulting in low-dimensional, less noisy updates. Empirical evaluation on natural language processing and computer vision tasks shows that our method outperforms other state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-07-06T14:09:47Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• Adaptive Gradient Method with Resilience and Momentum [120.83046824742455]
  We propose an Adaptive Gradient Method with Resilience and Momentum (AdaRem) AdaRem adjusts the parameter-wise learning rate according to whether the direction of one parameter changes in the past is aligned with the direction of the current gradient. Our method outperforms previous adaptive learning rate-based algorithms in terms of the training speed and the test error.
  arXiv  Detail & Related papers  (2020-10-21T14:49:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.