{
  "id": "2505.06902",
  "version": "v1",
  "published": "2025-05-11T08:51:15.000Z",
  "updated": "2025-05-11T08:51:15.000Z",
  "title": "Neuromodulation via Krotov-Hopfield Improves Accuracy and Robustness of RBMs",
  "authors": [
    "Başer Tambaş",
    "A. Levent Subaşı",
    "Alkan Kabakçıoğlu"
  ],
  "comment": "Submitted for publication",
  "categories": [
    "cond-mat.dis-nn"
  ],
  "abstract": "In biological systems, neuromodulation tunes synaptic plasticity based on the internal state of the organism, complementing stimulus-driven Hebbian learning. The algorithm recently proposed by Krotov and Hopfield \\cite{krotov_2019} can be utilized to mirror this process in artificial neural networks, where its built-in intra-layer competition and selective inhibition of synaptic updates offer a cost-effective remedy for the lack of lateral connections through a simplified attention mechanism. We demonstrate that KH-modulated RBMs outperform standard (shallow) RBMs in both reconstruction and classification tasks, offering a superior trade-off between generalization performance and model size, with the additional benefit of robustness to weight initialization as well as to overfitting during training.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2025-05-11T08:51:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "robustness",
      "neuromodulation tunes synaptic plasticity",
      "krotov-hopfield",
      "built-in intra-layer competition",
      "synaptic updates offer"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}