{
  "abstract": "The brain uses discrete spikes for dynamic computation, yet, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. Here, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computationally plausible explanation for the brain's learning mechanisms.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.08070",
  "author_total": 9,
  "authors": [
    {
      "name": "Xiangnan Zhang"
    },
    {
      "name": "Jingxin Liu"
    },
    {
      "name": "Ranqi Lu"
    },
    {
      "name": "Jingyu Liu"
    },
    {
      "name": "Qunxi Dong"
    },
    {
      "name": "Fuze Tian"
    },
    {
      "name": "Lixian Zhu"
    },
    {
      "name": "Bin Hu"
    },
    {
      "name": "Björn W. Schuller"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a9kk53ak0f8xs.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.08070",
  "fulltext_url": null,
  "id": "a9kk53ak0f8xs",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.08070",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "2208|Advanced Memory and Neural Computing"
    ]
  ],
  "openalex": "W7212041583",
  "pdf_url": "https://arxiv.org/pdf/2609.08070",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-10",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a9kk53ak0f8xs.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:31Z",
      "native_id": "2609.08070",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.08070"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits",
  "title_text": "A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:31Z",
  "url": "https://research.draconitic.com/paper/a9kk53ak0f8xs",
  "venue": "arXiv",
  "versions": []
}