Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity

2025-12-14

AI Summary

To address the rigidity of controller architectures and reliance on global error signals in deep reinforcement learning, this paper proposes an online adaptive neural network growth framework. The method employs local structural plasticity modules (SPMs), which drive topology evolution—neuron insertion and pruning—solely via local neuronal activation and gradient statistics, eliminating manual hyperparameter tuning. It supports both artificial neural networks (ANNs) and spiking neural networks (SNNs), establishing a novel brain-inspired paradigm for plasticity-based control. On standard control benchmarks, the approach achieves comparable or superior cumulative rewards while significantly reducing policy variance and automatically converging to compact, task-adapted architectures. Ablation studies confirm that structural plasticity is critical for reward stability and robust policy learning.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Behavior Learning & Control

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Control policies in deep reinforcement learning are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which lack structural plasticity and depend on global error signals. This paper introduces the Self-Motivated Growing Neural Network (SMGrNN), a controller whose topology evolves online through a local Structural Plasticity Module (SPM). The SPM monitors neuron activations and edge-wise weight update statistics over short temporal windows and uses these signals to trigger neuron insertion and pruning, while synaptic weights are updated by a standard gradient-based optimizer. This allows network capacity to be regulated during learning without manual architectural tuning. SMGrNN is evaluated on control benchmarks via policy distillation. Compared with multilayer perceptron baselines, it achieves similar or higher returns, lower variance, and task-appropriate network sizes. Ablation studies with growth disabled and growth-only variants isolate the role of structural plasticity, showing that adaptive topology improves reward stability. The local and modular design of SPM enables future integration of a Hebbian plasticity module and spike-timing-dependent plasticity, so that SMGrNN can support both artificial and spiking neural implementations driven by local rules.

Problem

• Adaptive neural network topology for reinforcement learning control
• Local structural plasticity to regulate capacity without manual tuning
• Improving reward stability and task-appropriate network size

Innovation

• Self-Motivated Growing Neural Network with local Structural Plasticity Module
• Neuron insertion and pruning based on activation and weight update statistics
• Local structural plasticity improves reward stability and regulates capacity