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

• URL: http://arxiv.org/abs/2512.12713v1
• Date: Sun, 14 Dec 2025 14:31:21 GMT
• Title: Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity
• Authors: Yiyang Jia, Chengxu Zhou,
• Abstract summary: 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.
• Score: 0.2578242050187029
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• PTS-SNN: A Prompt-Tuned Temporal Shift Spiking Neural Networks for Efficient Speech Emotion Recognition [12.087823767638788]
  Speech Emotion Recognition (SER) is widely deployed in Human-Computer Interaction, yet the high computational cost hinders their implementation on resource-constrained edge devices.<n>We propose Prompt-Tuned Spiking Neural Networks (PTS-SNN), a parameter-efficient neuromorphic adaptation with spiking dynamics.
  arXiv  Detail & Related papers  (2026-02-09T03:29:16Z)
• SpanNorm: Reconciling Training Stability and Performance in Deep Transformers [55.100133502295996]
  We propose SpanNorm, a novel technique designed to resolve the dilemma by integrating the strengths of both paradigms.<n>We provide a theoretical analysis demonstrating that SpanNorm, combined with a principled scaling strategy, maintains bounded signal variance throughout the network.<n> Empirically, SpanNorm consistently outperforms standard normalization schemes in both dense and Mixture-of-Experts (MoE) scenarios.
  arXiv  Detail & Related papers  (2026-01-30T05:21:57Z)
• Supervised Spike Agreement Dependent Plasticity for Fast Local Learning in Spiking Neural Networks [6.376927936764407]
  We introduce a supervised extension of Spike Agreement-Dependent Plasticity (SADP)<n>SADP replaces pairwise spike-timing comparisons with population-level agreement metrics such as Cohen's kappa.<n>Experiments on MNIST, Fashion-MNIST, CIFAR-10, and biomedical image classification tasks demonstrate competitive performance and fast convergence.
  arXiv  Detail & Related papers  (2026-01-13T13:09:34Z)
• Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning [58.533203990515034]
  Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL)<n>We show that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements.<n>We finally distill these insights into Module-Specific Training (MST), a practical framework that exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.
  arXiv  Detail & Related papers  (2025-10-14T03:03:08Z)
• Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning [2.3752592594044297]
  This paper presents a Spiking Neural Network (SNN) architecture for lifelong Network Intrusion Detection System (NIDS)<n>The proposed system first employs an efficient static SNN to identify potential intrusions, which then activates an adaptive dynamic SNN responsible for classifying the specific attack type.<n>Tested on the UNSW-NB15 benchmark in a continual learning setting, the architecture demonstrates robust adaptation, reduced catastrophic forgetting, and achieves $85.3$% overall accuracy.
  arXiv  Detail & Related papers  (2025-08-06T16:29:59Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• IP$^{2}$-RSNN: Bi-level Intrinsic Plasticity Enables Learning-to-learn in Recurrent Spiking Neural Networks [20.88195975299024]
  We develop a recurrent spiking neural network with bi-level intrinsic plasticity (IP$2$-RSNN)<n>Our results indicate that the proposed bi-level intrinsic plasticity plays a critical role in enabling L2L in RSNNs.
  arXiv  Detail & Related papers  (2025-01-24T14:45:03Z)
• Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement [62.91536661584656]
  We propose a dual-module framework, Cell-embedded and Feature-enhanced Graph Neural Network (aka, CeFeGNN) for learning.<n>We embed learnable cell attributions to the common node-edge message passing process, which better captures the spatial dependency of regional features.<n>Experiments on various PDE systems and one real-world dataset demonstrate that CeFeGNN achieves superior performance compared with other baselines.
  arXiv  Detail & Related papers  (2024-09-26T16:22:08Z)
• 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)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections [10.188771327458651]
  Spike-timing-dependent plasticity (STDP) is a general learning rule in the brain, but spiking neural networks (SNNs) trained with STDP alone is inefficient and perform poorly. We design an adaptive synaptic filter and introduce the adaptive spiking threshold to enrich the representation ability of SNNs. Our model achieves the current state-of-the-art performance of unsupervised STDP-based SNNs in the MNIST and FashionMNIST datasets.
  arXiv  Detail & Related papers  (2022-07-06T14:53:32Z)
• Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses [1.9809266426888898]
  Training spiking neural networks (RNNs) on dedicated neuromorphic hardware is still an open challenge. We present a simulation framework of differential-architecture arrays based on an accurate and comprehensive Phase-Change Memory (PCM) device model. We train a spiking RNN whose weights are emulated in the presented simulation framework, using a recently proposed e-prop learning rule.
  arXiv  Detail & Related papers  (2021-08-04T01:24:17Z)

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.