{"id":"https://openalex.org/W3090961927","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207535","title":"Improved Polynomial Neural Networks with Normalised Activations","display_name":"Improved Polynomial Neural Networks with Normalised Activations","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090961927","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207535","mag":"3090961927"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101826719","display_name":"Mohit Goyal","orcid":"https://orcid.org/0000-0002-8835-158X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohit Goyal","raw_affiliation_strings":["Electrical and Computer Engineering Dept., University of Illinois, Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Dept., University of Illinois, Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104039520","display_name":"Rajan Goyal","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajan Goyal","raw_affiliation_strings":["Electrical Engineering Dept., Indian Institute of Technology, Delhi"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Dept., Indian Institute of Technology, Delhi","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066116024","display_name":"Brejesh Lall","orcid":"https://orcid.org/0000-0003-2677-3071"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Brejesh Lall","raw_affiliation_strings":["Electrical Engineering Dept., Indian Institute of Technology, Delhi"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Dept., Indian Institute of Technology, Delhi","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101826719"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.761939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6778926849365234},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6232644319534302},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.547364354133606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363752841949463},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5183826088905334},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5141103863716125},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4524300694465637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3882281482219696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17498242855072021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6778926849365234},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6232644319534302},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.547364354133606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363752841949463},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5183826088905334},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5141103863716125},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4524300694465637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3882281482219696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17498242855072021},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494445008","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1572063013","https://openalex.org/W1836465849","https://openalex.org/W1899249567","https://openalex.org/W2029469881","https://openalex.org/W2062455387","https://openalex.org/W2101234009","https://openalex.org/W2113517874","https://openalex.org/W2166116275","https://openalex.org/W2194775991","https://openalex.org/W2788800397","https://openalex.org/W2798291370","https://openalex.org/W2886850811","https://openalex.org/W2914484425","https://openalex.org/W2946510242","https://openalex.org/W2947576584","https://openalex.org/W2949650786","https://openalex.org/W2952215077","https://openalex.org/W2952720005","https://openalex.org/W2963376662","https://openalex.org/W2963759574","https://openalex.org/W2964121744","https://openalex.org/W2964148965","https://openalex.org/W2999571325","https://openalex.org/W3125537303","https://openalex.org/W4288316086","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6639736602","https://openalex.org/W6675354045","https://openalex.org/W6676797890","https://openalex.org/W6680196509","https://openalex.org/W6681017033","https://openalex.org/W6687483927","https://openalex.org/W6737324275","https://openalex.org/W6748581759","https://openalex.org/W6750531877","https://openalex.org/W6753769513","https://openalex.org/W6759638512","https://openalex.org/W6763023700","https://openalex.org/W6764313071"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W4230611425","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Polynomials,":[0],"which":[1,74,126],"are":[2,37],"widely":[3],"used":[4,89],"to":[5,12,54,90,107,120,130,162,169],"study":[6,170],"non-linear":[7],"systems,":[8],"have":[9],"been":[10],"shown":[11],"be":[13,87,105,148],"extremely":[14],"useful":[15],"in":[16,94,151],"analyzing":[17],"neural":[18,27],"networks":[19,28,41],"(NNs).":[20],"However,":[21],"the":[22,55,76,156,159,164],"existing":[23],"methods":[24],"for":[25,39,67,96],"training":[26,60,79],"with":[29,47,81,124,133],"polynomial":[30],"activation":[31],"functions":[32],"(PAFs),":[33],"called":[34],"as":[35,98,100],"PNNs,":[36],"applicable":[38],"shallow":[40,92],"and":[42],"give":[43],"a":[44,64,70,118],"stable":[45],"performance":[46,128],"quadratic":[48],"PAFs":[49,68,125],"only.":[50],"This":[51,153],"is":[52],"due":[53],"optimization":[56],"issues":[57],"encountered":[58],"during":[59],"PNNs.":[61],"We":[62,115],"propose":[63,117],"working":[65],"model":[66],"using":[69,167],"novel":[71],"normalizing":[72],"transformation":[73],"alleviates":[75],"problem":[77],"of":[78,112,158],"PNNs":[80,93,146],"arbitrary":[82],"degree.":[83],"Our":[84],"PAF":[85],"can":[86,103,147],"directly":[88],"train":[91,121],"practice":[95],"degrees":[97],"high":[99],"ten.":[101],"It":[102],"also":[104,116,154],"utilized":[106],"learn":[108],"multivariate":[109],"sparse":[110],"polynomials":[111,168],"small":[113],"degrees.":[114],"way":[119],"deep":[122,131,171],"CNNs":[123,132],"achieve":[127],"similar":[129],"standard":[134],"activations.":[135],"Through":[136],"rigorous":[137],"experimentation":[138],"on":[139,166],"multiple":[140],"data":[141],"sets,":[142],"we":[143],"show":[144],"that":[145],"effectively":[149],"trained":[150],"practice.":[152],"highlights":[155],"potential":[157],"proposed":[160],"method":[161],"support":[163],"research":[165],"learning.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}