Methods › General › Initialization › LSUV Initialization

Layer-Sequential Unit-Variance Initialization

LSUV Initialization

1 paper tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Layer-Sequential Unit-Variance Initialization (LSUV) is a simple method for weight initialization for deep net learning. The initialization strategy involves the following two step:

1) First, pre-initialize weights of each convolution or inner-product layer with orthonormal matrices.

2) Second, proceed from the first to the final layer, normalizing the variance of the output of each layer to be equal to one.

Source: All you need is a good init

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

All you need is a good init
19 Nov 2015 · 11 repositories · arXiv:1511.06422

Syntology ran 0 of 19 samples · 19 unverified · 2 pointer-only (licence)

Tasks archive 2025-07-28

2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
All	1
Image Classification	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Initialization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections