{"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":"/method/maxout","slug":"maxout","name":"Maxout","full_name":"Maxout","full_name_withheld":false,"description_markdown":"The **Maxout Unit** is a generalization of the [ReLU](https://paperswithcode.com/method/relu) and the [leaky ReLU](https://paperswithcode.com/method/leaky-relu) functions. It is a piecewise linear function that returns the maximum of the inputs, designed to be used in conjunction with [dropout](https://paperswithcode.com/method/dropout). Both ReLU and leaky ReLU are special cases of Maxout. \r\n\r\n$$f\\left(x\\right) = \\max\\left(w^{T}\\_{1}x + b\\_{1}, w^{T}\\_{2}x + b\\_{2}\\right)$$\r\n\r\nThe main drawback of Maxout is that it is computationally expensive as it doubles the number of parameters for each neuron.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Maxout Networks","paper":"/paper/maxout-networks","first_author":"Ian J. Goodfellow","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/maxout-networks"},"source":{"url":"http://arxiv.org/abs/1302.4389v4","title":"Maxout Networks","url_on_a_paper_host":true},"code_snippet_url":"https://gist.github.com/daskol/05439f018465c8fb42ae547b8cc8a77b","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Activation Functions","url":"/methods/category/activation-functions","pwc_aliases":[]}],"n_papers_tagged":50,"archive_num_papers":50,"papers_newest_first":[{"paper":null,"slug":"deep-ice-the-first-globally-optimal-algorithm","title":"Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks","date":"2025-05-09","arxiv_id":"2505.05740","n_code_links":0,"syntology":null},{"paper":null,"slug":"depth-bounds-for-neural-networks-via-the","title":"Depth-Bounds for Neural Networks via the Braid Arrangement","date":"2025-02-13","arxiv_id":"2502.09324","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-maxout-network-based-feature-fusion-and","title":"Deep Maxout Network-based Feature Fusion and Political Tangent Search Optimizer enabled Transfer Learning for Thalassemia Detection","date":"2023-08-03","arxiv_id":"2308.02029","n_code_links":0,"syntology":null},{"paper":"/paper/query-structure-modeling-for-inductive","slug":"query-structure-modeling-for-inductive","title":"Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs","date":"2023-05-23","arxiv_id":"2305.13585","n_code_links":1,"syntology":null},{"paper":null,"slug":"error-bounds-for-maxout-neural-network","title":"Error bounds for maxout neural network approximations of model predictive control","date":"2023-04-18","arxiv_id":"2304.08779","n_code_links":0,"syntology":null},{"paper":"/paper/expected-gradients-of-maxout-networks-and","slug":"expected-gradients-of-maxout-networks-and","title":"Expected Gradients of Maxout Networks and Consequences to Parameter Initialization","date":"2023-01-17","arxiv_id":"2301.06956","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-maxout-network-gaussian-process","title":"Deep Maxout Network Gaussian Process","date":"2022-08-08","arxiv_id":"2208.04468","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-role-of-depth-width-and-activation","title":"On the Number of Regions of Piecewise Linear Neural Networks","date":"2022-06-17","arxiv_id":"2206.08615","n_code_links":0,"syntology":null},{"paper":"/paper/learning-with-stochastic-orders","slug":"learning-with-stochastic-orders","title":"Learning with Stochastic Orders","date":"2022-05-27","arxiv_id":"2205.13684","n_code_links":1,"syntology":null},{"paper":null,"slug":"smooth-maximum-unit-smooth-activation","title":"Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-discriminative-shrinkage-deep","slug":"learning-discriminative-shrinkage-deep","title":"Learning Discriminative Shrinkage Deep Networks for Image Deconvolution","date":"2021-11-27","arxiv_id":"2111.13876","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-frequency-localization-using-deep","title":"Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition","date":"2021-08-09","arxiv_id":"2108.03818","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-expected-complexity-of-maxout-networks","slug":"on-the-expected-complexity-of-maxout-networks","title":"On the Expected Complexity of Maxout Networks","date":"2021-07-01","arxiv_id":"2107.00379","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hanna-tseran/maxout_complexity"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"revisiting-2d-convolutional-neural-networks","title":"Revisiting 2D Convolutional Neural Networks for Graph-based Applications","date":"2021-05-23","arxiv_id":"2105.11016","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximum-and-leaky-maximum-propagation","title":"Maximum and Leaky Maximum Propagation","date":"2021-05-21","arxiv_id":"2105.10277","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-deep-convolutional","title":"Performance Evaluation of Deep Convolutional Maxout Neural Network in Speech Recognition","date":"2021-05-04","arxiv_id":"2105.01399","n_code_links":0,"syntology":null},{"paper":null,"slug":"sharp-bounds-for-the-number-of-regions-of","title":"Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums","date":"2021-04-16","arxiv_id":"2104.08135","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-semi-supervised-self-training-method","title":"A new semi-supervised self-training method for lung cancer prediction","date":"2020-12-17","arxiv_id":"2012.09472","n_code_links":0,"syntology":null},{"paper":"/paper/activate-or-not-learning-customized","slug":"activate-or-not-learning-customized","title":"Activate or Not: Learning Customized Activation","date":"2020-09-10","arxiv_id":"2009.04759","n_code_links":5,"syntology":null},{"paper":null,"slug":"deep-neural-kernel-machines","title":"Deep Neural-Kernel Machines","date":"2020-07-13","arxiv_id":"2007.06655","n_code_links":0,"syntology":null},{"paper":"/paper/cspnet-a-new-backbone-that-can-enhance","slug":"cspnet-a-new-backbone-that-can-enhance","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","date":"2019-11-27","arxiv_id":"1911.11929","n_code_links":123,"syntology":null},{"paper":null,"slug":"best-practices-for-convolutional-neural","title":"Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images","date":"2019-10-29","arxiv_id":"1910.13029","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-preserving-grid-layout-a-simple-graph","title":"Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs","date":"2019-09-26","arxiv_id":"1909.12383","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-learning-affine-invariant","title":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","date":"2019-08-31","arxiv_id":"1909.00114","n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-computation-for-continual","title":"Conditional Computation for Continual Learning","date":"2019-06-16","arxiv_id":"1906.06635","n_code_links":0,"syntology":null},{"paper":"/paper/max-plus-operators-applied-to-filter","slug":"max-plus-operators-applied-to-filter","title":"Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks","date":"2019-03-19","arxiv_id":"1903.08072","n_code_links":1,"syntology":null},{"paper":"/paper/paragraph-level-neural-question-generation","slug":"paragraph-level-neural-question-generation","title":"Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks","date":"2018-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"competition-vs-concatenation-in-skip","title":"Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks","date":"2018-07-20","arxiv_id":"1807.07803","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-tropical-approach-to-neural-networks-with","title":"A Tropical Approach to Neural Networks with Piecewise Linear Activations","date":"2018-05-22","arxiv_id":"1805.08749","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-image-super-resolution-using","title":"Single Image Super-Resolution Using Lightweight CNN with Maxout Units","date":"2017-11-07","arxiv_id":"1711.02321","n_code_links":0,"syntology":null},{"paper":null,"slug":"neuron-pruning-for-compressing-deep-networks","title":"Neuron Pruning for Compressing Deep Networks using Maxout Architectures","date":"2017-07-21","arxiv_id":"1707.06838","n_code_links":0,"syntology":null},{"paper":"/paper/adversarially-learned-inference","slug":"adversarially-learned-inference","title":"Adversarially Learned Inference","date":"2016-06-02","arxiv_id":"1606.00704","n_code_links":9,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["IshmaelBelghazi/ALI"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/the-ibm-2016-english-conversational-telephone","slug":"the-ibm-2016-english-conversational-telephone","title":"The IBM 2016 English Conversational Telephone Speech Recognition System","date":"2016-04-27","arxiv_id":"1604.08242","n_code_links":0,"syntology":null},{"paper":"/paper/dehazenet-an-end-to-end-system-for-single","slug":"dehazenet-an-end-to-end-system-for-single","title":"DehazeNet: An End-to-End System for Single Image Haze Removal","date":"2016-01-28","arxiv_id":"1601.07661","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-unified-gradient-regularization-family-for","title":"A Unified Gradient Regularization Family for Adversarial Examples","date":"2015-11-19","arxiv_id":"1511.06385","n_code_links":0,"syntology":null},{"paper":null,"slug":"manifold-regularized-deep-neural-networks","title":"Manifold Regularized Deep Neural Networks using Adversarial Examples","date":"2015-11-19","arxiv_id":"1511.06381","n_code_links":0,"syntology":null},{"paper":"/paper/competitive-multi-scale-convolution","slug":"competitive-multi-scale-convolution","title":"Competitive Multi-scale Convolution","date":"2015-11-18","arxiv_id":"1511.05635","n_code_links":0,"syntology":null},{"paper":"/paper/a-light-cnn-for-deep-face-representation-with","slug":"a-light-cnn-for-deep-face-representation-with","title":"A Light CNN for Deep Face Representation with Noisy Labels","date":"2015-11-09","arxiv_id":"1511.02683","n_code_links":19,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AlfredXiangWu/LightCNN","AlfredXiangWu/face_verification_experiment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/batch-normalized-maxout-network-in-network","slug":"batch-normalized-maxout-network-in-network","title":"Batch-normalized Maxout Network in Network","date":"2015-11-09","arxiv_id":"1511.02583","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/on-the-importance-of-normalisation-layers-in","slug":"on-the-importance-of-normalisation-layers-in","title":"On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units","date":"2015-08-03","arxiv_id":"1508.00330","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-maxout-features","title":"Random Maxout Features","date":"2015-06-11","arxiv_id":"1506.03705","n_code_links":0,"syntology":null},{"paper":"/paper/the-ibm-2015-english-conversational-telephone","slug":"the-ibm-2015-english-conversational-telephone","title":"The IBM 2015 English Conversational Telephone Speech Recognition System","date":"2015-05-21","arxiv_id":"1505.05899","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-microaneurysm-detection-using-deep","title":"Improved Microaneurysm Detection using Deep Neural Networks","date":"2015-05-17","arxiv_id":"1505.04424","n_code_links":0,"syntology":null},{"paper":"/paper/training-deep-neural-networks-with-low","slug":"training-deep-neural-networks-with-low","title":"Training deep neural networks with low precision multiplications","date":"2014-12-22","arxiv_id":"1412.7024","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-number-of-linear-regions-of-deep","title":"On the Number of Linear Regions of Deep Neural Networks","date":"2014-02-08","arxiv_id":"1402.1869","n_code_links":0,"syntology":null},{"paper":"/paper/improving-deep-neural-networks-with","slug":"improving-deep-neural-networks-with","title":"Improving Deep Neural Networks with Probabilistic Maxout Units","date":"2013-12-20","arxiv_id":"1312.6116","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-maxout-to-channel-out-encoding","title":"From Maxout to Channel-Out: Encoding Information on Sparse Pathways","date":"2013-11-18","arxiv_id":"1312.1909","n_code_links":0,"syntology":null},{"paper":null,"slug":"learned-norm-pooling-for-deep-feedforward-and","title":"Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks","date":"2013-11-07","arxiv_id":"1311.1780","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-text-recognition-with-hybrid-hmm","title":"End-to-End Text Recognition with Hybrid HMM Maxout Models","date":"2013-10-07","arxiv_id":"1310.1811","n_code_links":0,"syntology":null},{"paper":"/paper/maxout-networks","slug":"maxout-networks","title":"Maxout Networks","date":"2013-02-18","arxiv_id":"1302.4389","n_code_links":7,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}}],"papers_shown":50,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":50,"with_a_code_link":15,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":50,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/method/maxout/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/maxout/papers/ran/1","json":"/method/maxout/papers/ran/1.json","rows":4}],"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":9},{"task":"/task/classification","name":"General Classification","papers":8},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":4},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":3},{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/face-verification","name":"Face Verification","papers":2},{"task":"/task/graph-classification","name":"Graph Classification","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/object-recognition","name":"Object Recognition","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/computed-tomography-ct","name":"Computed Tomography (CT)","papers":1}],"tasks_shown":20,"n_tasks":52,"usage_by_year":[{"year":"2013","papers":5},{"year":"2014","papers":2},{"year":"2015","papers":9},{"year":"2016","papers":3},{"year":"2017","papers":2},{"year":"2018","papers":3},{"year":"2019","papers":6},{"year":"2020","papers":3},{"year":"2021","papers":7},{"year":"2022","papers":4},{"year":"2023","papers":4},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/maxout"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Maxout","read_at":"2026-10-05T00:58:58+00:00","query":"Maxout","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1302.4389","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Maxout' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"9fee1d3471ca86094a09d61647a059ba0cb967db6059cc3d48dd63b754b06962","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}