diplomsko delo
Nejc Graj (Author), Iztok Fister (Mentor), Grega Vrbančič (Co-mentor)

Abstract

V tem diplomskem delu bomo predstavili področje strojnega učenja, bolj specifično področje globokega učenja. V teoretičnem delu bomo prikazali, kako se je strojno učenje do sedaj že uporabljalo v športu, kako strojno in globoko učenje delujeta ter kako poteka proces učenja konvolucijskih nevronskih mrež. V praktičnem delu bomo ustvarili svojo učno množico in nato z algoritmom, ki je zasnovan na konvolucijskih nevronskih mrežah, ustvarili model, ki je zmožen določati uspešnost počepa po pravilih zveze za Powerlifting.

Keywords

strojni vid;globoko učenje;konvolucijske nevronske mreže;powerlifting;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. Graj]
UDC: 004.8796.88(043.2)
COBISS: 220206083 Link will open in a new window
Views: 0
Downloads: 12
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: Determining squat depth with the help of machine vision
Secondary abstract: In this diploma thesis, we will delve into the field of machine learning, specifically focusing on the area of deep learning. In the theoretical part, we will examine how machine learning has been until now used in sports and as well as how machine learning, deep learning, and the process of training convolutional neural networks work. In the practical part, we will create our own training dataset and use an algorithm based on convolutional neural networks to create a model capable of assessing the performance of a squat according to the rules of the International Powerlifting Federation.
Secondary keywords: machine learning;deep learning;convolutional neural networks;powerlifting;bachelor's degrees;
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Informatika in tehnologije komuniciranja
Pages: 1 spletni vir (1 datoteka PDF (XII, 40 f.))
ID: 24420254