second-brain

Home

❯

nodes

❯

Surrogate Gradient Learning

Surrogate Gradient Learning

01 sept 2026Se lee en 1 min

  • snn

○ unseen · kind algorithm · level 0 · 4h

  • Aplica: Spiking Neural Network (SNN)
  • Requiere: Backpropagation

Trains SNNs by replacing the non-differentiable spike with a smooth surrogate during the backward pass. Effective, but essentially backprop in disguise — not biologically plausible.

Enlaces

  • Aplica: Spiking Neural Network (SNN)
  • Requiere: Backpropagation

Vista Gráfica

Retroenlaces

  • second-brain
  • snnTorch

Notas Recientes

  • second-brain

    01 sept 2026

  • A/B Testing

    01 sept 2026

  • Action Potential (Spike)

    01 sept 2026

  • Activation Functions

    01 sept 2026

  • Actor-Critic Methods

    01 sept 2026

  • Actor Model

    01 sept 2026

  • AdEx Neuron

    01 sept 2026

  • Adversarial Attacks

    01 sept 2026

Creado con Quartz v4.5.2 © 2026

  • GitHub
  • Grafo local-first