Home › Code › relu

relu

Syntologyentry name in harvested coderead from the graph 2026-09-24

relu appears in the code Syntology harvested for 58 papers, as 49 distinct code bodies found in 60 places (a place is one code body under one paper). At least one of them ran in 27 of the papers; 16 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named relu do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 19 of the 49 distinct code bodies named relu; 30 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

10ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
0ran · fixture could not drive it
7ran
30unverified
16fingerprinted

Licence is a property of each copy, so it is counted per place: 14 of the 60 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

58 papers shown of 58, newest first; 60 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 4 papers added by Syntology; 2 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
Robust Dual-Model Collaborative Random Vector Functional Link Network added by Syntology 2026-08 (from id) identical code first harvested elsewhere 1dbace35862da027 ran · honoured contract fingerprinted licence of this copy not recorded
Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets added by Syntology 2026-07 (from id) xavimaass/dropout_and_ram_2026/src/jax_resnet/activations.py bb3e244596afa241 ran fingerprinted no licence file found · pointer only
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings added by Syntology 2026-04 (from id) UCSB-NLP-Chang/Skill-Usage/terminal-bench-2/model-extraction-relu-logits/environment/forward.py 68ee2675b183b56f unverified no licence file found · pointer only
A Fully First-Order Layer for Differentiable Optimization added by Syntology 2025-12 (from id) GT-KOALA/FFOLayer/baselines/AltDiff.py 75a806c121e013d2 unverified MIT (permissive)
Zero-shot forecasting of chaotic systems 24 Sep 2024 williamgilpin/dysts/dysts/metrics.py c9d8d9901e3c6aab ran fingerprinted Apache-2.0 (permissive)
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers 16 Jul 2024 SPOC-group/counting-attention/manual_models.py df689d0142c2d3c9 ran fingerprinted no licence file found · pointer only
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning 10 Jun 2024 allanraventos/getrichquick/two-layer-relu/utils.py c0a59302e913313d ran MIT (permissive)
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features 5 Feb 2024 simone-bombari/attention-sensitivity/utils.py 9d27f9aa50a86a4b ran fingerprinted no licence file found · pointer only
Tight Verification of Probabilistic Robustness in Bayesian Neural Networks 21 Jan 2024 benbatten/TightVerificationOfProbabilisticRobustnessInBNNs/verifier/utils.py 5af8fa537914ff3d ran · honoured contract fingerprinted no licence file found · pointer only
The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models 19 Dec 2023 pilancilab/convex_nn/convex_nn.py 1dbace35862da027 ran · honoured contract fingerprinted no licence file found · pointer only
Microscaling Data Formats for Deep Learning 16 Oct 2023 microsoft/microxcaling/mx/activations.py 4490c20d2c5ae00e unverified MIT (permissive)
Neural Relational Inference with Fast Modular Meta-learning 10 Oct 2023 FerranAlet/modular-metalearning/layers.py 8dd8a8e3eac0253a ran fingerprinted MIT (permissive)
Automatic Integration for Spatiotemporal Neural Point Processes 9 Oct 2023 rose-stl-lab/autostpp/src/demo/CorrectingMLE.py 5af8fa537914ff3d ran · honoured contract fingerprinted MIT (permissive)
Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction 3 Sep 2023 lpcccc-cv/MC-CDic/models/modules/MCCDic.py e87a5885334f0de1 unverified MIT (permissive)
A Rainbow in Deep Network Black Boxes 29 May 2023 florentinguth/rainbow/models/Analysis.py 1a2d7d179b6fcef3 unverified BSD-3-Clause (permissive)
Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models 14 Mar 2023 keras-team/keras/keras/src/activations/activations.py 59c7dca60305d651 unverified Apache-2.0 (permissive)
Learning to Backdoor Federated Learning 6 Mar 2023 HengerLi/RLBackdoorFL/Util.py 65bc749ceadcf87d unverified MIT (permissive)
Boundary-Aware Uncertainty for Feature Attribution Explainers 5 Oct 2022 davinhill/gpec/GPEC/utils/utils_np.py 5af8fa537914ff3d ran · honoured contract fingerprinted MIT (permissive)
Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization 26 May 2022 identical code first harvested elsewhere 1dbace35862da027 ran · honoured contract fingerprinted licence of this copy not recorded
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias 13 Dec 2021 virajmehta/vae-training/utils.py 2cc5c094d751d00a unverified MIT (permissive)
On the Existence of Universal Lottery Tickets 22 Nov 2021 relationalml/universallt/subsetsum.py 4c9a9cab68f5a375 ran · honoured contract fingerprinted no licence file found · pointer only
On Transferability of Prompt Tuning for Natural Language Processing 12 Nov 2021 thunlp/Prompt-Transferability/Prompt-Transferability-1.0/activate_neuron_Roberta.py 5a45143bbc682622 unverified MIT (permissive)
Phase Collapse in Neural Networks 11 Oct 2021 florentinguth/phasecollapse/models/Analysis.py 1a2d7d179b6fcef3 unverified BSD-3-Clause (permissive)
RECALL: Replay-based Continual Learning in Semantic Segmentation 8 Aug 2021 LTTM/RECALL/model_resnet.py 37e49142da9ee0cd ran · honoured contract fingerprinted MIT (permissive)
Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness 26 May 2021 xxxnell/spatial-smoothing/models/smoothing_block.py d419f818792d3793 ran Apache-2.0 (permissive)
Analytical bounds on the local Lipschitz constants of ReLU networks 29 Apr 2021 uwaa-ndcl/local_lipschitz/network_bound.py 7bc22741366e8140 unverified MIT (permissive)
SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs 25 Feb 2021 nn4pde/SPINN/automate.py 93a27674bbe152a1 ran · honoured contract fingerprinted licence not identified · pointer only
Principled Simplicial Neural Networks for Trajectory Prediction 19 Feb 2021 nglaze00/scone_gcn/trajectory_analysis/trajectory_experiments.py 4e5209e332ac17d2 unverified MIT (permissive)
Separation and Concentration in Deep Networks 18 Dec 2020 j-zarka/separation_concentration_deepnets/models/Analysis.py d5d46e42d48015f4 ran · our draft was wrong fingerprinted BSD-3-Clause (permissive)
Neural Architecture Search without Training 8 Jun 2020 nlinc1905/evolutionary-reinforcement-learner/models/mlp.py 0bd581e0afb4c04a unverified MIT (permissive)
Black-box Mixed-Variable Optimisation using a Surrogate Model that Satisfies Integer Constraints 8 Jun 2020 lbliek/MVRSM/MVRSM.py 5778be44d14bcb09 ran · honoured contract fingerprinted MIT (permissive)
Neural Additive Models: Interpretable Machine Learning with Neural Nets 29 Apr 2020 Habush/nam_jax/models.py 454cfa9b8b9aed47 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Neural Additive Models: Interpretable Machine Learning with Neural Nets 29 Apr 2020 nickfrosst/neural_additive_models/models.py 207a3a66ecdc0f2f ran · honoured contract fingerprinted no licence file found · pointer only
Cryptanalytic Extraction of Neural Network Models 10 Mar 2020 google-research/cryptanalytic-model-extraction/check_solution_svd.py 5af8fa537914ff3d ran · honoured contract fingerprinted Apache-2.0 (permissive)
Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules 6 Jan 2020 LiuLei95/PyTorch-Learned-Image-Compression-with-GMM-and-Attention/models/basics.py ba24f201a717509b unverified Apache-2.0 (permissive)
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression 19 Nov 2019 grifon-239/diploma/common/backbones/mobilenet_v3.py d304c126a9501818 unverified MIT (permissive)
Deep Network Classification by Scattering and Homotopy Dictionary Learning 8 Oct 2019 j-zarka/SparseScatNet/models/ISTC.py d5d46e42d48015f4 ran · our draft was wrong fingerprinted BSD-3-Clause (permissive)
A Fine-Grained Spectral Perspective on Neural Networks 24 Jul 2019 thegregyang/NNspectra/theory.py 5af8fa537914ff3d ran · honoured contract fingerprinted MIT (permissive)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 rohitgr7/tvmodels/tvmodels/models/blocks/effnet_blocks.py 9461188086a155ec ran · our draft was wrong MIT (permissive)
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning 15 May 2019 likesiwell/LGM-Net/meta_matching_network.py ba415e733a64978f unverified MIT (permissive)
Language-Conditioned Graph Networks for Relational Reasoning 10 May 2019 ronghanghu/lcgn/models_clevr/ops.py 2de8a558c3e97e3d unverified BSD-2-Clause (permissive)
RetinaFace: Single-stage Dense Face Localisation in the Wild 2 May 2019 StanislasBertrand/RetinaFace-tf2/src/retinafacetf2/networks/network_utils.py c24c719cc4022d0b unverified MIT (permissive)
Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation 31 Oct 2018 amansinha/neural-bridge/envs/car_racing/WorldModel/dream_model.py b4ffc7174f63b5d9 ran · honoured contract fingerprinted MIT (permissive)
Stochastic Hyperparameter Optimization through Hypernetworks 26 Feb 2018 lorraine2/hypernet-hypertraining/code/neural_network.py 57d85d9dbc47f39e unverified MIT (permissive)
2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning 26 Feb 2018 dluvizon/deephar/deephar/layers.py 401ff7831c3db2d1 unverified MIT (permissive)
Learning to Generalize: Meta-Learning for Domain Generalization 10 Oct 2017 HAHA-DL/MLDG/ops.py 982640b2b87ab733 unverified MIT (permissive)
Learning to Generalize: Meta-Learning for Domain Generalization 10 Oct 2017 Pulkit-Khandelwal/mldg/ops.py ffc6304fe71748bf unverified Apache-2.0 (permissive)
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations 10 Mar 2017 dtak/rrr/rrr/multilayer_perceptron.py fd6644bff4456444 unverified MIT (permissive)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks 9 Mar 2017 katerakelly/pytorch-maml/src/layers.py 8dd8a8e3eac0253a ran fingerprinted MIT (permissive)
QCD-Aware Recursive Neural Networks for Jet Physics 2 Feb 2017 glouppe/recnn/recnn/recnn.py ef94bdd1ea899a09 unverified BSD-3-Clause (permissive)
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation 28 Nov 2016 ankit-vaghela30/Cilia-Segmentation/hastings/tiramisu_model.py a5b43c4ed0ec9709 unverified MIT (permissive)
iCaRL: Incremental Classifier and Representation Learning 23 Nov 2016 srebuffi/iCaRL/iCaRL-Tensorflow/utils_resnet.py 4c8201151d6e4d18 unverified MIT (permissive)
End-to-end Optimized Image Compression 5 Nov 2016 liujiaheng/iclr_17_compression/models/basics.py ba24f201a717509b unverified MIT (permissive)
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization 7 Oct 2016 ryoasu/grad-cam/keras_pkg/grad_cam.py b4ffc7174f63b5d9 ran · honoured contract fingerprinted no licence file found · pointer only
Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation 18 Mar 2016 Kamnitsask/deepmedic/deepmedic/neuralnet/ops.py 5d605f64da7a03e1 unverified BSD-3-Clause (permissive)
Convolutional Networks on Graphs for Learning Molecular Fingerprints 30 Sep 2015 HIPS/neural-fingerprint/neuralfingerprint/build_vanilla_net.py cba23591b86550d5 unverified MIT (permissive)
U-Net: Convolutional Networks for Biomedical Image Segmentation 18 May 2015 ChengBinJin/U-Net-TensorFlow/src/model.py 2746cf1ccebe4079 unverified no licence file found · pointer only
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification 6 Feb 2015 hamiddimyati/dd2424-deep-learning/assignment-2/assignment2-bonus.py 94d5729d92a97933 ran · honoured contract fingerprinted no licence file found · pointer only
arXiv:aaai_5987 RingBDStack/MA-GCNNs/M-GCNNs/layers.py df2e36697d20ae04 unverified MIT (permissive)
arXiv:aaai_17756 kia-kia/IC-MLNet/model/ops.py 8ec69db6155c57f6 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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