SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1607.06450 · arXiv.org · 2016

Layer Normalization

Geoffrey Hinton, Jamie Kiros, Jimmy Lei Ba

arXiv · PDF · Open in the Atlas

Code that ran

7 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 10 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1607.06450.json · badge: /api/ran/1607.06450.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
daehwannam/pytorch-rnn-util community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
kienduynguyen/Layer-Normalization community
Papers with Code archive
2 ran · 0 no recorded run
cyh1112/GraphNormalization community
Papers with Code archive
1 ran · 0 no recorded run
HarmanDotpy/Normalizations-in-Deep-Learning community
Papers with Code archive
1 ran · 0 no recorded run
JeffreyJosanne/nematus_tf community
Papers with Code archive
1 ran · 0 no recorded run
zhangyaoyuan/GAN-Simplification community
Papers with Code archive
0 ran · 4 no recorded run
ElektrischesSchaf/LayerNorm_GRU community
Papers with Code archive
0 ran · 1 no recorded run
bhaddow/dev-nematus community
Papers with Code archive
0 ran · 1 no recorded run
wri/restoration-mapper community
Papers with Code archive
0 ran · 1 no recorded run
JRC1995/Machine-Translation-Transformers community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
GraphNorm Ran
ran on a synthesized input · constructed an object; no result was computed
cyh1112/GraphNormalization/norm/graph_norm.py
pointer only (licence: NOASSERTION) · get_code("7d881e4088f29595")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, cyh1112/GraphNormalization (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
kienduynguyen/Layer-Normalization/LayerNorm.py
pointer only (licence: NONE) · get_code("74c1444feed033d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kienduynguyen/Layer-Normalization when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LayerNorm2D Ran
ran on a synthesized input · constructed an object; no result was computed
HarmanDotpy/Normalizations-in-Deep-Learning/Normalisations.py
code served (permissive licence) · get_code("94ce18ebe841264e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, LayerNorm2D: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function is LayerNorm2D.__init__ and LayerNorm2D.forward
# We need to construct arguments for instantiating LayerNorm2D and for calling forward

# From the __init__ signature:
# - num_channels: int (required)
# - epsilon: float (optional, default=1e-05)

# From the forward method, x must be:
# - a 4D tensor (batch, channels, height, width)
# - x.shape[1] must equal num_channels

num_channels = 4
batch_size = 2
height = 3
width = 5

# Create a sample input tensor for forward pass
x = torch.randn(batch_size, num_channels, height, width)

ARGS = {
    "num_channels": num_channels,
    "epsilon": 1e-05,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LayerNorm2D — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a LayerNorm2D output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LayerNormLayer Ran
ran on a synthesized input · constructed an object; no result was computed
JeffreyJosanne/nematus_tf/nematus/layers.py
code served (permissive licence) · get_code("ea323f4fc8005e6d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, LayerNormLayer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy

# Create LayerNormLayer instances with valid arguments
layer_size = 4
eps = 1e-5

ARGS = {
    'layer_size': layer_size,
    'eps': eps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LayerNormLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a LayerNormLayer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_lstm_cell_init_state Ran
ran on a synthesized input
daehwannam/pytorch-rnn-util/rnnlib/common.py
code served (permissive licence) · get_code("b29f84a895c28c9c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "hidden_size": 4,
    "init_state_learned": True,
    "device": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_indicator Ran
ran on a synthesized input
daehwannam/pytorch-rnn-util/rnnlib/common.py
code served (permissive licence) · get_code("f1b57d3c5218cd84")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 5, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct length_tensor - a tensor containing sequence lengths
# Using a small batch of 2 with different lengths
length_tensor = torch.tensor([3, 5], dtype=torch.int64)

# max_length parameter - optional, can be None or an integer
# If None, the function will use length_tensor.max()
max_length = None

ARGS = {
    "length_tensor": length_tensor,
    "max_length": max_length,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 5, 1) — shape (2, 5, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
layer_norm Ran
ran on a synthesized input · constructed an object; no result was computed
kienduynguyen/Layer-Normalization/LayerNorm.py
pointer only (licence: NONE) · get_code("def0b163983628e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kienduynguyen/Layer-Normalization when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LayerNormGRUCell Not yet run
unverified (harvested, no recorded run)
ElektrischesSchaf/LayerNorm_GRU/GRU_layernorm_cell.py
code served (permissive licence) · get_code("4455b0c0adbcbe75")
How it ran

no invocation recorded.

LayerNormLayer Not yet run
unverified (harvested, no recorded run)
bhaddow/dev-nematus/nematus/layers.py
code served (permissive licence) · get_code("c12ea25352a4dd86")
How it ran

no invocation recorded.

forward_rnn Not yet run
unverified (harvested, no recorded run)
daehwannam/pytorch-rnn-util/rnnlib/seq.py
code served (permissive licence) · get_code("626f734fb412461b")
How it ran

no invocation recorded.

group_norm Not yet run
unverified (harvested, no recorded run)
wri/restoration-mapper/src/layers/extra_layers.py
pointer only (licence: GPL-3.0) · get_code("29bb6248ac270983")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, wri/restoration-mapper, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

layer_norm Not yet run
unverified (harvested, no recorded run)
JRC1995/Machine-Translation-Transformers/Machine Translation.py
code served (permissive licence) · get_code("0050dfbf8ad7677a")
How it ran

no invocation recorded.

layer_norm Not yet run
unverified (harvested, no recorded run)
zhangyaoyuan/GAN-Simplification/tensor2tensor/common_layers.py
pointer only (licence: NONE) · get_code("caa1927febb58775")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyaoyuan/GAN-Simplification when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

layer_norm_compute Not yet run
unverified (harvested, no recorded run)
zhangyaoyuan/GAN-Simplification/tensor2tensor/common_layers.py
pointer only (licence: NONE) · get_code("f61aa475517589c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyaoyuan/GAN-Simplification when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

layer_norm_compute_grad Not yet run
unverified (harvested, no recorded run)
zhangyaoyuan/GAN-Simplification/tensor2tensor/common_layers.py
pointer only (licence: NONE) · get_code("56c490283a6d5297")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyaoyuan/GAN-Simplification when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

layer_norm_compute_python Not yet run
unverified (harvested, no recorded run)
zhangyaoyuan/GAN-Simplification/tensor2tensor/common_layers.py
pointer only (licence: NONE) · get_code("80444e734e109863")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyaoyuan/GAN-Simplification when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

repeat_lstm_cell_state Not yet run
unverified (harvested, no recorded run)
daehwannam/pytorch-rnn-util/rnnlib/common.py
code served (permissive licence) · get_code("14170af1a02b42f5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 16 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
layer_norm_compute_python
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1603.01547 (2016-03)
Text Understanding with the Attention Sum Reader Network

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute a mean and variance which are then used to normalize the summed input to that neuron on each training case. This significantly reduces the training time in feedforward neural networks. However, the effect of batch normalization is dependent on the mini-batch size and it is not obvious how to apply it to recurrent neural networks. In this paper, we transpose batch normalization into layer normalization by computing the mean and variance used for normalization from all of the summed inputs to the neurons in a layer on a single training case. Like batch normalization, we also give each neuron its own adaptive bias and gain which are applied after the normalization but before the non-linearity. Unlike batch normalization, layer normalization performs exactly the same computation at training and test times. It is also straightforward to apply to recurrent neural networks by computing the normalization statistics separately at each time step. Layer normalization is very effective at stabilizing the hidden state dynamics in recurrent networks. Empirically, we show that layer normalization can substantially reduce the training time compared with previously published techniques.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1607.06450")
get_code_for_paper("1607.06450")
have("1607.06450")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1607.06450.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1607.06450.svg)](https://syntology.ai/paper/1607.06450)

Connect an agent — have() is free.