Papers › Training Full Spike Neural Networks via Auxiliary Accumulation Pathway

Training Full Spike Neural Networks via Auxiliary Accumulation Pathway

27 Jan 2023arXiv:2301.11929archive 2025-07-28

Guangyao Chen, Peixi Peng, Guoqi Li, Yonghong Tian

Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention. However, the binary spike propagation of the Full-Spike Neural Networks (FSNN) with limited time steps is prone to significant information loss. To improve performance, several state-of-the-art SNN models trained from scratch inevitably bring many non-spike operations. The non-spike operations cause additional computational consumption and may not be deployed on some neuromorphic hardware where only spike operation is allowed. To train a large-scale FSNN with high performance, this paper proposes a novel Dual-Stream Training (DST) method which adds a detachable Auxiliary Accumulation Pathway (AAP) to the full spiking residual networks. The accumulation in AAP could compensate for the information loss during the forward and backward of full spike propagation, and facilitate the training of the FSNN. In the test phase, the AAP could be removed and only the FSNN remained. This not only keeps the lower energy consumption but also makes our model easy to deploy. Moreover, for some cases where the non-spike operations are available, the APP could also be retained in test inference and improve feature discrimination by introducing a little non-spike consumption. Extensive experiments on ImageNet, DVS Gesture, and CIFAR10-DVS datasets demonstrate the effectiveness of DST.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2301.11929")

Code

Syntology Ran 8 of 11 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 4 ran; named in the paper: 7 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

iCGY96/AAP officialmentioned on GitHubpytorchMIT report
iCGY96/syops-counter mentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 8 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
1ran · fixture could not drive it
5ran
3unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

accuracy iCGY96/AAP/imagenet/utils.py official repository ran · fixture could not drive it MIT (permissive) · 4134b8420b4c48b5 · report
conv1x1 iCGY96/AAP/imagenet/dsnn.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 iCGY96/AAP/imagenet/dsnn.py official repository ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
convpxp iCGY96/AAP/imagenet/dsnn.py official repository ran MIT (permissive) · 79233a0a481d1c39 · report
params_to_string iCGY96/syops-counter/syops/utils.py named in the paper ran MIT (permissive) · dc5ee8c0a918c502 · report
rnn_syops iCGY96/syops-counter/syops/ops.py named in the paper ran MIT (permissive) · ff0de6ad446ac5df · report
spike_rate iCGY96/syops-counter/syops/ops.py named in the paper ran MIT (permissive) · 315b7f4d135390d6 · report
syops_to_string iCGY96/syops-counter/syops/utils.py named in the paper ran MIT (permissive) · eda2bc4c9144c14c · report
accumulate_syops iCGY96/syops-counter/syops/engine.py named in the paper unverified MIT (permissive) · e805c6a2a25d5e39 · report
get_model_complexity_info iCGY96/syops-counter/syops/flops_counter.py named in the paper unverified MIT (permissive) · 49528bea8c87044b · report
print_model_with_syops iCGY96/syops-counter/syops/engine.py named in the paper unverified MIT (permissive) · 11ca743c5945e560 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DSTTest

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