{"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/heterogeneous-multilayer-generalized","title":"Heterogeneous Multilayer Generalized Operational Perceptron","arxiv_id":"1804.05093","date":"2018-04-13","proceeding":null,"authors":["Dat Thanh Tran","Serkan Kiranyaz","Moncef Gabbouj","Alexandros Iosifidis"],"abstract":"The traditional Multilayer Perceptron (MLP) using McCulloch-Pitts neuron\nmodel is inherently limited to a set of neuronal activities, i.e., linear\nweighted sum followed by nonlinear thresholding step. Previously, Generalized\nOperational Perceptron (GOP) was proposed to extend conventional perceptron\nmodel by defining a diverse set of neuronal activities to imitate a generalized\nmodel of biological neurons. Together with GOP, Progressive Operational\nPerceptron (POP) algorithm was proposed to optimize a pre-defined template of\nmultiple homogeneous layers in a layerwise manner. In this paper, we propose an\nefficient algorithm to learn a compact, fully heterogeneous multilayer network\nthat allows each individual neuron, regardless of the layer, to have distinct\ncharacteristics. Based on the complexity of the problem, the proposed algorithm\noperates in a progressive manner on a neuronal level, searching for a compact\ntopology, not only in terms of depth but also width, i.e., the number of\nneurons in each layer. The proposed algorithm is shown to outperform other\nrelated learning methods in extensive experiments on several classification\nproblems.","url_abs":"http://arxiv.org/abs/1804.05093v3","url_pdf":"http://arxiv.org/pdf/1804.05093v3.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":[{"paper_slug":"heterogeneous-multilayer-generalized","repo_url":"https://github.com/viebboy/PyGOP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}