mlsanityData to 14 Oct 2026

The Neural Division of Labor: Biologically-Inspired Modular Architectures for Robust Neuromorphic Computing

arXiv 2608.08317 ↗First posted 8 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Biological neural systems achieve high efficiency and robustness through compartmentalized architectures. In contrast, modern artificial neural networks rely on globally entangled structures, which obscure decision logic and suffer from catastrophic forgetting. Here, we report a Decomposable Spiking Neural Network (D-SNN) that eliminates global synaptic entanglement by structurally isolating classification pathways into independent experts. Optimized via a bio-inspired push-pull loss function, the D-SNN achieves competitive accuracies on MNIST, Fashion-MNIST, and CIFAR-10/100 benchmarks. This modular approach matches the performance of fully dense networks while utilizing an order of magnitude fewer parameters. In addition, our networks operate with up to several orders of magnitude lower firing rates and fewer synaptic operations. Furthermore, physically severing connections between experts provides inherent protection against catastrophic forgetting during sequential learning. Crucially, these isolated pathways generate auditable neural signals, increasing decision transparency. This biomimetic, verifiable architecture establishes an efficient foundation for deploying deterministic neuromorphic intelligence in resource-constrained edge environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 88 references that are in the map. First posted on arXiv 8 Aug 2026.

Builds on

33 of 88 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2016Learning without Forgettingcited by 2,496
  9. 2020Concept Bottleneck Modelscited by 1,032
  10. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  11. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  12. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
21 more
  1. 2018Deep Learning in Spiking Neural Networkscited by 263
  2. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
  3. 2017An Introduction to Deep Learning for the Physical Layercited by 233
  4. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  5. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 205
  6. 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 179
  7. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 144
  8. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 122
  9. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 103
  10. 2022Interactive Concept Bottleneck Modelscited by 79
  11. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 72
  12. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 71
  13. 2015Spiking Deep Networks with LIF Neuronscited by 63
  14. 2020Brain-Inspired Learning on Neuromorphic Substratescited by 37
  15. 2018A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rulecited by 36
  16. 2025Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2cited by 8
  17. 2022Benchmarking energy consumption and latency for neuromorphic computing in condensed matter and particle physicscited by 5
  18. 2025Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stabilitycited by 5
  19. 2021Efficient Training of Spiking Neural Networks with Temporally-Truncated Local Backpropagation through Timecited by 3
  20. 2026Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimizationcited by 1
  21. 2026Binary Spiking Neural Networks as Causal Modelscited by 1

Built on by

Not cited yet.