SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.13271 · IJCAI · 2022

Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes

Yang Li, Yi Zeng

arXiv · PDF · Open in the Atlas

Code that ran

3 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 3 have no contract verdict; 0 failures of our instrument; 0 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/2204.13271.json · badge: /api/ran/2204.13271.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
brain-inspired-cognitive-engine/conversion_burst canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
evaluate_accuracy Ran
ran on a synthesized input
brain-inspired-cognitive-engine/conversion_burst/utils.py
code served (permissive licence) · get_code("d4a07d38b7cf02dc")
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 float, ndim 0, dtype family float, shape () 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
import torch.nn as nn
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Create a simple neural network
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Create model
net = SimpleNet()

# Create small dataset
X = torch.randn(2, 4)
y = torch.tensor([0, 1])
dataset = TensorDataset(X, y)
data_iter = DataLoader(dataset, batch_size=2)

# Get device from model parameters
device = list(net.parameters())[0].device

# Define all arguments
ARGS = {
    'data_iter': data_iter,
    'net': net,
    'device': device,
    'only_onebatch': False,
    'ind': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
fuse Ran
ran on a synthesized input
brain-inspired-cognitive-engine/conversion_burst/converted_CIFAR100_vgg.py
code served (permissive licence) · get_code("ed2d3062f64fa847")
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 Conv2d. 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)

# Create a simple Conv2d layer
conv = nn.Conv2d(in_channels=3, out_channels=4, kernel_size=3, stride=1, padding=1, bias=True)

# Create a BatchNorm2d layer
bn = nn.BatchNorm2d(num_features=4)

# Initialize the BatchNorm with some running statistics
# (BatchNorm needs to be run in eval mode or we manually set running stats)
bn.eval()
bn.running_mean = torch.randn(4)
bn.running_var = torch.ones(4) * 0.5
bn.weight = nn.Parameter(torch.randn(4))
bn.bias = nn.Parameter(torch.randn(4))
bn.eps = 1e-5

ARGS = {
    "conv": conv,
    "bn": bn
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
load_imagenet Ran
ran on a synthesized input
brain-inspired-cognitive-engine/conversion_burst/utils.py
code served (permissive licence) · get_code("75cc5caa4b6be46f")
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 os
import torch
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import tempfile
import shutil
from PIL import Image

torch.manual_seed(0)

# Create temporary directory structure for ImageNet
temp_root = tempfile.mkdtemp()
train_dir = os.path.join(temp_root, 'train')
val_dir = os.path.join(temp_root, 'val')

# Create class subdirectories
os.makedirs(os.path.join(train_dir, 'class1'), exist_ok=True)
os.makedirs(os.path.join(val_dir, 'class1'), exist_ok=True)

# Create dummy images for training
for i in range(2):
    img = Image.new('RGB', (256, 256), color=(i * 50, i * 50, i * 50))
    img.save(os.path.join(train_dir, 'class1', f'train_img_{i}.jpg'))

# Create dummy images for validation
for i in range(2):
    img = Image.new('RGB', (256, 256), color=(i * 100, i * 100, i * 100))
    img.save(os.path.join(val_dir, 'class1', f'val_img_{i}.jpg'))

ARGS = {
    'root': temp_root,
    'batch_size': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — 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

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

Spiking neural network (SNN), as a brain-inspired energy-efficient neural network, has attracted the interest of researchers. While the training of spiking neural networks is still an open problem. One effective way is to map the weight of trained ANN to SNN to achieve high reasoning ability. However, the converted spiking neural network often suffers from performance degradation and a considerable time delay. To speed up the inference process and obtain higher accuracy, we theoretically analyze the errors in the conversion process from three perspectives: the differences between IF and ReLU, time dimension, and pooling operation. We propose a neuron model for releasing burst spikes, a cheap but highly efficient method to solve residual information. In addition, Lateral Inhibition Pooling (LIPooling) is proposed to solve the inaccuracy problem caused by MaxPooling in the conversion process. Experimental results on CIFAR and Im-ageNet demonstrate that our algorithm is efficient and accurate. For example, our method can ensure nearly lossless conversion of SNN and only use about 1/10 (less than 100) simulation time under 0.693× energy consumption of the typical method. Our code is available at https://github.com/Brain-Inspired-Cognitive-Engine/Conversion Burst.

For agents

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

get_harvested_code_for_paper("2204.13271")
get_code_for_paper("2204.13271")
have("2204.13271")

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

curl https://syntology.ai/api/ran/2204.13271.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.13271.svg)](https://syntology.ai/paper/2204.13271)

Connect an agent — have() is free.