NeuroSynth: A Biologically Inspired Continual Reinforcement Learning Architecture for Mitigating Catastrophic Forgetting

• URL: http://arxiv.org/abs/2607.28663v1
• Date: Fri, 24 Jul 2026 05:56:07 GMT
• Title: NeuroSynth: A Biologically Inspired Continual Reinforcement Learning Architecture for Mitigating Catastrophic Forgetting
• Abstract summary: Artificial Intelligence (AI) systems often perform well on isolated tasks but struggle under continual learning conditions.<n>This study introduces Neuro Synth, a brain-inspired continual reinforcement learning architecture designed to mitigate catastrophic forgetting.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial Intelligence (AI) systems often perform well on isolated tasks but struggle under continual learning conditions, where training on new tasks can overwrite previously acquired knowledge, a failure mode known as catastrophic forgetting. Biological learning systems reduce this interference through complementary memory processes involving rapid hippocampal encoding and slower cortical consolidation. This study introduces NeuroSynth, a brain-inspired continual reinforcement learning architecture designed to mitigate catastrophic forgetting through a dual-pathway consolidation mechanism. NeuroSynth separates rapid task acquisition from long-term retention using distinct "plan" and "habit" pathways combined with replay and knowledge distillation. NeuroSynth was evaluated against Proximal Policy Optimization (PPO) and Elastic Weight Consolidation (EWC) across three sequential navigation tasks with changing goal locations in a non-revisitation continual learning setting. Across six independent seeds, NeuroSynth preserved substantially more early-task knowledge than PPO after sequential training, achieving 18.00% Task A success rate compared to 0.33% for PPO (p = 0.014929, Cohen's d = 1.49) and 35.33% Task B success rate compared to 0.00% for PPO (p = 0.002376, Cohen's d = 2.31). NeuroSynth also demonstrated higher final Task C performance than EWC, achieving 9.00% compared to 2.00% (p = 0.226643, Cohen's d = 0.56), indicating a moderate but not statistically significant advantage. These findings suggest that biologically inspired consolidation mechanisms may improve the stability-plasticity balance in continual reinforcement learning systems.

Related papers

• Progressive Generalization Augmentation with Deeply Coupled RND-PPO and Domain-Prioritized Noise Injection for Robust Crop Management Reinforcement Learning [3.0094301461257476]
  This paper tackles three limitations impeding practical deployment of agricultural RL systems.<n>We introduce three systematic innovations: Progressive Generalization Augmentation (PGA) implementing a three-phase curriculum; a deeply coupled RND-PPO architecture with dual-channel GAE normalization, progress-decayed intrinsic coefficients, and semantic discretization; and domain-prioritized noise injection with hierarchical activation.
  arXiv  Detail & Related papers  (2026-05-17T12:48:47Z)
• DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement Learning [62.347535250646196]
  This paper proposes DeFRiS, a Decentralized Federated Reinforcement Learning framework for robust and scalable Silo-cooperative IoT application scheduling.<n>DeFRiS integrates three innovations: (i) an action-space-agnostic policy utilizing candidate resource scoring to enable seamless knowledge transfer across heterogeneous silos; (ii) a silo-optimized local learning mechanism combining Generalized Advantage Estimation with clipped policy updates to resolve sparse delayed reward challenges; and (iii) a Dual-Track Non-IID robust decentralized aggregation protocol leveraging gradient fingerprints for similarity-aware knowledge transfer and anomaly detection.
  arXiv  Detail & Related papers  (2026-03-16T02:02:38Z)
• General Self-Prediction Enhancement for Spiking Neurons [71.01912385372577]
  Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs among performance, efficiency, and biological plausibility.<n>We propose a self-prediction enhanced spiking neuron method that generates an internal prediction current from its input-output history to modulate membrane potential.<n>This design offers dual advantages, it creates a continuous gradient path that alleviates vanishing gradients and boosts training stability and accuracy, while also aligning with biological principles, which resembles distal dendritic modulation and error-driven synaptic plasticity.
  arXiv  Detail & Related papers  (2026-01-29T15:08:48Z)
• FSC-Net: Fast-Slow Consolidation Networks for Continual Learning [0.0]
  We propose a dual-network architecture that separates rapid task learning from gradual knowledge consolidation.<n>Our method employs a fast network (NN1) for immediate adaptation to new tasks and a slow network (NN2) that consolidates knowledge through distillation and replay.<n>Our results provide empirical evidence that the dual-scale consolidation mechanism, rather than architectural complexity, is central to mitigating catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-11-12T15:42:33Z)
• Overcoming catastrophic forgetting in neural networks [0.0]
  Catastrophic forgetting is the primary challenge that hinders continual learning.<n> Elastic Weight Consolidation is a regularization-based approach inspired by synaptic consolidation in biological neural systems.<n>Our results confirm what was shown in previous research, showing that EWC significantly reduces forgetting compared to naive training.
  arXiv  Detail & Related papers  (2025-07-14T17:04:05Z)
• Extending Spike-Timing Dependent Plasticity to Learning Synaptic Delays [50.45313162890861]
  We introduce a novel learning rule for simultaneously learning synaptic connection strengths and delays.<n>We validate our approach by extending a widely-used SNN model for classification trained with unsupervised learning.<n>Results demonstrate that our proposed method consistently achieves superior performance across a variety of test scenarios.
  arXiv  Detail & Related papers  (2025-06-17T21:24:58Z)
• Stochastic Engrams for Efficient Continual Learning with Binarized Neural Networks [4.014396794141682]
  We propose a novel approach that integrates plasticityally-activated engrams as a gating mechanism for metaplastic binarized neural networks (mBNNs)<n>Our findings demonstrate (A) an improved stability vs. a trade-off, (B) a reduced memory intensiveness, and (C) an enhanced performance in binarized architectures.
  arXiv  Detail & Related papers  (2025-03-27T12:21:00Z)
• Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration [28.75006029656076]
  In this paper, we introduce SSDE, a novel structure-based approach that enhances plasticity through a fine-grained allocation strategy.<n>SSDE decomposes the parameter space into forward-transfer (frozen) parameters and task-specific (trainable) parameters.<n>Experiments on the CW10-v1 Continual World benchmark demonstrate that SSDE achieves state-of-the-art performance, reaching a success rate of 95%.
  arXiv  Detail & Related papers  (2025-03-07T08:58:07Z)
• Hebbian Deep Learning Without Feedback [0.0]
  We present SoftHebb, an algorithm that trains deep neural networks without any feedback, target, or error signals. Its increased efficiency and biological compatibility do not trade off accuracy compared to state-of-the-art bio-plausible learning.
  arXiv  Detail & Related papers  (2022-09-23T23:12:59Z)
• Continual learning benefits from multiple sleep mechanisms: NREM, REM, and Synaptic Downscaling [51.316408685035526]
  Learning new tasks and skills in succession without losing prior learning is a computational challenge for both artificial and biological neural networks. Here, we investigate how modeling three distinct components of mammalian sleep together affects continual learning in artificial neural networks.
  arXiv  Detail & Related papers  (2022-09-09T13:45:27Z)
• Towards Scaling Difference Target Propagation by Learning Backprop Targets [64.90165892557776]
  Difference Target Propagation is a biologically-plausible learning algorithm with close relation with Gauss-Newton (GN) optimization. We propose a novel feedback weight training scheme that ensures both that DTP approximates BP and that layer-wise feedback weight training can be restored. We report the best performance ever achieved by DTP on CIFAR-10 and ImageNet.
  arXiv  Detail & Related papers  (2022-01-31T18:20:43Z)
• Equilibrium Propagation with Continual Weight Updates [69.87491240509485]
  We propose a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT) We prove theoretically that, provided the learning rates are sufficiently small, at each time step of the second phase the dynamics of neurons and synapses follow the gradients of the loss given by BPTT. These results bring EP a step closer to biology by better complying with hardware constraints while maintaining its intimate link with backpropagation.
  arXiv  Detail & Related papers  (2020-04-29T14:54:30Z)

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.