🛠️ Steven Gong

Search

SearchSearch

Aug 24, 2025, 1 min read

Laplace Distribution

First saw reading this article https://semianalysis.com/2024/01/11/neural-network-quantization-and-number/

They’re essentially very sharp Gaussian Distributions.

“In practice, neural networks are typically normal or laplace distributed”.

f(x∣μ,b)=2b1​exp(−b∣x−μ∣​),−∞<x<∞

Graph View

Backlinks

  • Learning to Drive from a World Model

Created with Quartz, © 2025

  • Blog
  • LinkedIn
  • Twitter
  • GitHub