SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.01018 · 2022

Normalization effects on deep neural networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2209.01018.json · badge: /api/ran/2209.01018.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
kspiliopoulos/NENN_Deep canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
determine_device Ran
ran on a synthesized input
kspiliopoulos/NENN_Deep/functions.py
code served (permissive licence) · get_code("5c403003338fa67b")
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 device. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

def determine_device(do_print):
    """Determine whether to run the model on CPU or GPU
    
    Parameters
    ----------
    do_print: bool
        if True, print the device to be used
    """
    if torch.cuda.is_available():
        if do_print:
            print('Device:     GPU')
        device = torch.device('cuda')
    else:
        if do_print:
            print('Device:     CPU')
        device = torch.device('cpu')
    return device


torch.manual_seed(0)

ARGS = {
    'do_print': True
}
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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
run_model Ran
ran on a synthesized input
kspiliopoulos/NENN_Deep/functions.py
code served (permissive licence) · get_code("d9b4cdcd24c77672")
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 DataFrame. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import torch.optim as optim
from torch.utils.data import DataLoader

torch.manual_seed(0)

# Define a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 10)
    
    def forward(self, x):
        x = torch.relu(self.linear1(x))
        x = self.linear2(x)
        return x

# Create fake data: list of (inputs, targets) tuples
def create_fake_loader(num_samples=4):
    data = []
    for _ in range(num_samples):
        inputs = torch.randn(2, 4)  # batch size 2, input dim 4
        targets = torch.randint(0, 10, (2,))  # batch size 2, 10 classes
        data.append((inputs, targets))
    return data

# Instantiate components
model = SimpleModel()
optimizer = optim.SGD(model.parameters(), lr=0.01)
criterion = nn.MSELoss()
train_loader = create_fake_loader(num_samples=2)
test_loader = create_fake_loader(num_samples=2)
device = torch.device("cpu")
do_encoding = True
epochs = 2

ARGS = {
    "model": model,
    "optimizer": optimizer,
    "criterion": criterion,
    "train_loader": train_loader,
    "test_loader": test_loader,
    "device": device,
    "do_encoding": do_encoding,
    "epochs": epochs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
load_mnist_data Not yet run
unverified (harvested, no recorded run)
kspiliopoulos/NENN_Deep/functions.py
code served (permissive licence) · get_code("a1e0ec5d447e0b8e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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 2026-11-22.

Repositories linked to this paper

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

Abstract

We study the effect of normalization on the layers of deep neural networks of feed-forward type. A given layer $i$ with $N_{i}$ hidden units is allowed to be normalized by $1/N_{i}^{γ_{i}}$ with $γ_{i}\in[1/2,1]$ and we study the effect of the choice of the $γ_{i}$ on the statistical behavior of the neural network's output (such as variance) as well as on the test accuracy on the MNIST data set. We find that in terms of variance of the neural network's output and test accuracy the best choice is to choose the $γ_{i}$'s to be equal to one, which is the mean-field scaling. We also find that this is particularly true for the outer layer, in that the neural network's behavior is more sensitive in the scaling of the outer layer as opposed to the scaling of the inner layers. The mechanism for the mathematical analysis is an asymptotic expansion for the neural network's output. An important practical consequence of the analysis is that it provides a systematic and mathematically informed way to choose the learning rate hyperparameters. Such a choice guarantees that the neural network behaves in a statistically robust way as the $N_i$ grow to infinity.

For agents

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

get_harvested_code_for_paper("2209.01018")
get_code_for_paper("2209.01018")
have("2209.01018")

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

curl https://syntology.ai/api/ran/2209.01018.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.01018.svg)](https://syntology.ai/paper/2209.01018)

Connect an agent — have() is free.