Unverified50% confidenceFactExact time

Xavier initialization was proposed by Glorot in 2010 and He initialization was proposed by He et al. in 2015; their variances are designed to be 1/n and 2/n respectively (where n is the input dimension).

1

Sources

50%

Confidence

Long-term

Relevance

8/31/2026

First Seen

Sources

Coding Machine Learning Probability Distributions from Scratch: A Practical Guide to Gaussian, Beta, and Gamma Distributions

Related Entities

Xavier初始化concept He初始化concept

Related Claims

UnverifiedXavier initialization was proposed by Xavier Glorot in 2010, sampling weights from a distribution with mean 0 and variance 2/(n_in + n_out), and is suitable for symmetric activation functions such as Sigmoid/Tanh.75% similar UnverifiedHe初始化针对ReLU激活函数设计，通过将权重方差设为2/n来保证各层激活值方差稳定53% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/830023

API

curl https://kongchang.com/api/v1/knowledge/claims/830023

MCP

get_claim(id=830023)