SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.02944 · IJCAI · 2020

Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network

Qinru Qiu, Haowen Fang, Amar Shrestha, Ziyi Zhao

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 5 have no contract verdict; 0 failures of our instrument; 3 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/2003.02944.json · badge: /api/ran/2003.02944.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
zhongyuchen/snn-iir community (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
Snow-Crash/snn-iir marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_conv2d_outsize Ran
ran on a synthesized input
zhongyuchen/snn-iir/snn_lib/snn_layers.py
code served (permissive licence) · get_code("742e61bf511fd17f")
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, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# Simple test case for calculate_conv2d_outsize
# All parameters are integers or simple numeric types

ARGS = {
    "h_input": 32,
    "w_input": 32,
    "padding": 1,
    "kernel_size": 3,
    "stride": 1,
    "dilation": 1
}
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, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
calculate_maxpooling2d_outsize Ran
ran on a synthesized input
zhongyuchen/snn-iir/snn_lib/snn_layers.py
code served (permissive licence) · get_code("2c729eb2f09f605f")
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, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

# Construct arguments for calculate_maxpooling2d_outsize
# The function calculates output size of max pooling 2D given input dimensions and pooling parameters

ARGS = {
    "h_input": 28,
    "w_input": 32,
    "padding": 1,
    "kernel_size": 3,
    "stride": 2,
    "dilation": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
dual_exp_iir_cell Ran
ran on a synthesized input
Snow-Crash/snn-iir/snn_lib/snn_layers.py
pointer only (licence: NONE) · get_code("752537ad51396d53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Snow-Crash/snn-iir 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.

get_optimizer Ran
ran on a synthesized input
zhongyuchen/snn-iir/snn_lib/optimizers.py
code served (permissive licence) · get_code("882b7e8c0897682d")
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 Adam. 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 model with parameters
model = nn.Linear(4, 3)
params = model.parameters()

# Create configuration dictionary with optimizer settings
conf = {
    'optimizer': {
        'optimizer_choice': 'Adam',
        'Adam': {
            'lr': 0.001
        },
        'AdamW': {
            'lr': 0.0005
        },
        'SGD': {
            'lr': 0.01
        }
    }
}

ARGS = {
    'params': params,
    'conf': conf
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
get_scheduler Ran
ran on a synthesized input
zhongyuchen/snn-iir/snn_lib/schedulers.py
code served (permissive licence) · get_code("c3554bfa9c4e2e4e")
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 MultiStepLR. 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 model
model = nn.Linear(4, 2)

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

# Create a config dict for MultiStepLR scheduler
conf = {
    'scheduler': {
        'scheduler_choice': 'MultiStepLR',
        'MultiStepLR': {
            'milestones': [10, 20, 30],
            'gamma': 0.1
        }
    }
}

ARGS = {
    'optimizer': optimizer,
    'conf': conf
}
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 MultiStepLR — a MultiStepLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiStepLR 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
get_rand_transform Not yet run
unverified (harvested, no recorded run)
zhongyuchen/snn-iir/snn_lib/data_loaders.py
code served (permissive licence) · get_code("2887d40773413167")
How it ran

no invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
zhongyuchen/snn-iir/snn_conv_1_gesture.py
code served (permissive licence) · get_code("a557a6000459cb5f")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
zhongyuchen/snn-iir/snn_conv_1_gesture.py
code served (permissive licence) · get_code("d7e4ada9731bd191")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

The recently discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications. However designing large-scale and high-performance model is yet a challenge due to the lack of robust training algorithms. A bio-plausible SNN model with spatialtemporal property is a complex dynamic system. Synapses and neurons behave as filters capable of preserving temporal information. As such neuron dynamics and filter effects are ignored in existing training algorithms, the SNN downgrades into a memoryless system and loses the ability of temporal signal processing. Furthermore, spike timing plays an important role in information representation, but conventional rate-based spike coding models only consider spike trains statistically, and discard information carried by its temporal structures. To address the above issues, and exploit the temporal dynamics of SNNs, we formulate SNN as a network of infinite impulse response (IIR) filters with neuron nonlinearity. We proposed a training algorithm that is capable to learn spatial-temporal patterns by searching for the optimal synapse filter kernels and weights. The proposed model and training algorithm are applied to construct associative memories and classifiers for synthetic and public datasets including MNIST, NMNIST, DVS 128 etc. Their accuracy outperforms state-of-the-art approaches.

For agents

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

get_harvested_code_for_paper("2003.02944")
get_code_for_paper("2003.02944")
have("2003.02944")

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

curl https://syntology.ai/api/ran/2003.02944.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.02944.svg)](https://syntology.ai/paper/2003.02944)

Connect an agent — have() is free.