diplomsko delo
Nejc Planer (Author), Danilo Korže (Mentor), Mladen Borovič (Co-mentor)

Abstract

V diplomskem delu so predstavljene rekurentne nevronske mreže in primer njihove uporabe. V prvem delu je razloženo njihovo delovanje in vrsti nevronov, od katerih se kasneje uporabi celica LSTM (dolgo-kratko ročna spominska celica). To je aplicirano tudi na primerih napovedovanja zmagovalca, ali pade več kot 1,5 ali 2,5 gola na tekmo in ali obe ekipi zadeneta. Napovedljivost zmagovalca ligaških tekem je od 61 do 72 odstotkov, zmagovalca nogometnih turnirjev pa od 65 do 70 odstotkov. Uporabljene so angleška, francoska, italijanska, nemška, španska in slovenska liga ter tekmovanji Copa America in svetovno prvenstvo.

Keywords

napovedovanje;rekurentne nevornske mreže;celica LSTM;nogomet;umetna inteligenca;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [N. Planer]
UDC: 004.032.26(043.2)
COBISS: 22578198 Link will open in a new window
Views: 1427
Downloads: 224
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Predicting football match winner with LSTM recurrent neural network
Secondary abstract: This diploma thesis presents recurrent neural networks and example of their usage. In the first part it is explained how they work and their types of neurons of which LSTM cell is later used. This is applied on the examples of predicting football match winner, whether there are more than 1,5 or 2,5 goals per game and whether both teams score. The predictability of football league match winner is from 61 to 72 percent and football tournament winner from 65 to 70 percent. Used leagues are from England, France, Germany, Spain and Slovenia and tournaments Copa America and World Cup.
Secondary keywords: prediction;recurrent neural network;LSTM cell;football;artificial intelligence;
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: VII, 40 str.
ID: 11194660