{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/parametric-exponential-linear-unit-for-deep","title":"Parametric Exponential Linear Unit for Deep Convolutional Neural Networks","arxiv_id":"1605.09332","date":"2016-05-30","proceeding":null,"authors":["Ludovic Trottier","Philippe Giguère","Brahim Chaib-Draa"],"abstract":"Object recognition is an important task for improving the ability of visual\nsystems to perform complex scene understanding. Recently, the Exponential\nLinear Unit (ELU) has been proposed as a key component for managing bias shift\nin Convolutional Neural Networks (CNNs), but defines a parameter that must be\nset by hand. In this paper, we propose learning a parameterization of ELU in\norder to learn the proper activation shape at each layer in the CNNs. Our\nresults on the MNIST, CIFAR-10/100 and ImageNet datasets using the NiN,\nOverfeat, All-CNN and ResNet networks indicate that our proposed Parametric ELU\n(PELU) has better performances than the non-parametric ELU. We have observed as\nmuch as a 7.28% relative error improvement on ImageNet with the NiN network,\nwith only 0.0003% parameter increase. Our visual examination of the non-linear\nbehaviors adopted by Vgg using PELU shows that the network took advantage of\nthe added flexibility by learning different activations at different layers.","url_abs":"http://arxiv.org/abs/1605.09332v4","url_pdf":"http://arxiv.org/pdf/1605.09332v4.pdf","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":[],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"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":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"elu","method_name":"ELU"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pelu","method_name":"PELU"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pelu","name":"PELU","full_name":"Parametric Exponential Linear Unit"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.09332","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}