{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/trainable-activations-for-image","title":"Trainable Activations for Image Classification","arxiv_id":null,"date":"2023-01-26","proceeding":"Preprints 2023 1","authors":["Evgenii Pishchik"],"abstract":"Non-linear activation functions are one of the main parts of deep neural network architectures. The choice of the activation function can affect model speed, performance and convergence. Most popular activation functions don't have any trainable parameters and don't alter during the training. We propose different activation functions with and without trainable parameters. Said activation functions have a number of advantages and disadvantages. We'll be testing the performance of said activation functions and comparing the results with widely known activation function ReLU. We assume that the activation functions with trainable parameters can outperform functions without ones, because the trainable parameters allow the model to \"select'' the type of each of the activation functions itself, however, this strongly depends on the architecture of the deep neural network and the activation function itself.","url_abs":"https://doi.org/10.20944/preprints202301.0463.v1","url_pdf":"https://www.preprints.org/manuscript/202301.0463/v1/download","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"trainable-activations-for-image","repo_url":"https://github.com/Pe4enIks/TrainableActivation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"coslu","method_name":"CosLU"},{"method_slug":"delu","method_name":"DELU"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lincomb","method_name":"LinComb"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"normlincomb","method_name":"NormLinComb"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"relu6","method_name":"ReLU6"},{"method_slug":"relun","method_name":"ReLUN"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"scaledsoftsign","method_name":"ScaledSoftSign"},{"method_slug":"shilu","method_name":"ShiLU"},{"method_slug":"silu","method_name":"SiLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softsign-activation","method_name":"Softsign Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"coslu","name":"CosLU","full_name":"Cosine Linear Unit"},{"slug":"delu","name":"DELU","full_name":"DELU"},{"slug":"lincomb","name":"LinComb","full_name":"Linear Combination of Activations"},{"slug":"normlincomb","name":"NormLinComb","full_name":"Normalized Linear Combination of Activations"},{"slug":"relun","name":"ReLUN","full_name":"Rectified Linear Unit N"},{"slug":"scaledsoftsign","name":"ScaledSoftSign","full_name":"ScaledSoftSign"},{"slug":"shilu","name":"ShiLU","full_name":"Shifted Rectified Linear Unit"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-26 (Trainable Activations)","rank_in_archive_order":196,"of":265,"metrics":{"Percentage correct":"91.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-32 (Trainable Activations)","rank_in_archive_order":197,"of":265,"metrics":{"Percentage correct":"90.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-44 (Trainable Activations)","rank_in_archive_order":204,"of":265,"metrics":{"Percentage correct":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-20 (Trainable Activations)","rank_in_archive_order":205,"of":265,"metrics":{"Percentage correct":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-14 (Trainable Activations)","rank_in_archive_order":212,"of":265,"metrics":{"Percentage correct":"89.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-56 (Trainable Activations)","rank_in_archive_order":215,"of":265,"metrics":{"Percentage correct":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet-8 (Trainable Activations)","rank_in_archive_order":228,"of":265,"metrics":{"Percentage correct":"86.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"DNN-5 (Trainable Activations)","rank_in_archive_order":59,"of":81,"metrics":{"Accuracy":"97.2","Percentage error":"2.8","Trainable Parameters":"575051"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"DNN-3 (Trainable Activations)","rank_in_archive_order":60,"of":81,"metrics":{"Accuracy":"97.0","Percentage error":"3.0","Trainable Parameters":"386719"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"DNN-2 (Trainable Activations)","rank_in_archive_order":61,"of":81,"metrics":{"Accuracy":"96.4","Percentage error":"3.6","Trainable Parameters":"311651"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"Pe4enIks/TrainableActivation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7a4dcdc87b2364ded54a35b5f038aa0c6da1f01408238364b502ec5275215265","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}