| fullrecord |
[{"key": "dc.contributor.advisor", "value": "Taipalus, Toni", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Lappalainen, Markus", "language": "", "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2023-06-01T06:53:26Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2023-06-01T06:53:26Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2023", "language": "", "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/87381", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Koneoppimisalgoritmit ja neuroverkot ovat nyky\u00e4\u00e4n osa jokap\u00e4iv\u00e4ist\u00e4 el\u00e4m\u00e4\u00e4mme, ja niiden tuoma kehitys on mullistanut yhteiskunnan montaa osa-aluetta. Nopean kehityksen vuoksi asiaan perehtym\u00e4t\u00f6n henkil\u00f6 tuskin yleens\u00e4 edes huomaa k\u00e4ytt\u00e4v\u00e4ns\u00e4 koneoppimiseen perustuvia teknologioita. Koneoppiminen, ja varsinkin neuroverkot, ovat nyky\u00e4\u00e4n niin monimutkaisia, ett\u00e4 niiden toimintaa voi olla vaikeaa, tai jopa mahdotonta ymm\u00e4rt\u00e4\u00e4. Tutkimus toteutettiin kuvailevana kirjallisuuskatsauksena. Tutkimuksessa annetaan ensin lyhyt yleiskatsaus koneoppimisesta lukijan ymm\u00e4rryksen tueksi. Tutkimuksen p\u00e4\u00e4tarkoitus, sek\u00e4 tutkimusongelma, oli selvitt\u00e4\u00e4 koneoppimisty\u00f6kalujen toimintaperiaatteet. Tutkimusongelmaa selvitettiin tutustumalla koneoppimisty\u00f6-kalujen toimintaan, etenkin niiden opetusvaiheeseen, jonka aikana luodaan edellytykset niiden p\u00e4\u00e4t\u00f6ksenteolle. Tutkimuksessa selvitettiin joidenkin suosittujen koneoppimisty\u00f6kalujen toimintaperiaatteita, sek\u00e4 esitell\u00e4\u00e4n ne helppolukuisessa ja helposti ymm\u00e4rrett\u00e4v\u00e4ss\u00e4 muodossa, ilman matemaattisia kaavoja. Koneoppimisty\u00f6kalujen perustoimintaperiaatteeksi l\u00f6ydettiin virhefunktiot, ja niiden minimoiminen. Virhefunktiot esitt\u00e4v\u00e4t koneoppimisty\u00f6kalun ennusteen ja toteutuneen tapahtuman v\u00e4list\u00e4 eroa, joten virhefunktion minimoiminen on koneoppimisen ydintavoite. Keinot virhefunktioiden minimoimiseksi riippuu k\u00e4sitelt\u00e4v\u00e4n koneoppimisty\u00f6kalun piirteist\u00e4. Tarkasteltaessa valittujen koneoppimisty\u00f6kalujen optimointiongelmia, paljastui yleisimm\u00e4ksi keinoksi gradienttimenetelm\u00e4\u00e4n perustuvat iteratiiviset optimointialgoritmit. Tutkimuksen aikana l\u00f6ytyi my\u00f6s muita optimointiongelmia, joita ei pystyt\u00e4 ratkaisemaan gradienttimenetelm\u00e4ll\u00e4. Tutkimuksen aikana selvisi my\u00f6s koneoppimisen perustuvan vahvasti matematiikkaan, erityisesti lineaarialgebraan sek\u00e4 derivointiin.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Machine learning algorithms and neural networks are a ubiquitous part of our everyday lives, and their recent development has revolutionized many areas of society. Due to the rapid pace of development, a person who is not familiar with the subject may not even realize that they are using technologies based on machine learning. Machine learning, especially neural networks, are now so complex that understanding the logic behind their decision can sometimes be impossible. The study was conducted as a descriptive literature review. The study begins by providing a brief overview of machine learning to support the reader's understanding. The main objective of the study, and the research question, was to clarify the basic principles of machine learning tools. This was done by examining the operation of machine learning tools, particularly their training phase, during which the conditions for their decision-making are established. The study examined the operating principles of some popular machine learning tools and presented them in an easy-to-understand form, without mathematical formulas. The basic operating principle of machine learning tools was found to be cost functions and their minimization. Cost functions measure the difference between the prediction of the machine learning tool and the actual outcome, so minimizing the cost function can be seen as the primary goal of machine learning. The method for minimizing a cost function depends on the characteristics of the machine learning tool being used. When examining the optimization methods of the studied machine learning tools, iterative optimization algorithms based on the gradient descent algorithm were found to be the most common approach. The study also identified other optimization problems that cannot be solved by the gradient descent algorithm. At the time of writing the study, it became clear that machine learning is heavily based on mathematics, especially linear algebra, and differentiation.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Paivi Vuorio (paelvuor@jyu.fi) on 2023-06-01T06:53:26Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2023-06-01T06:53:26Z (GMT). No. of bitstreams: 0\n Previous issue date: 2023", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "28", "language": "", "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.language.iso", "value": "fin", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "In Copyright", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.title", "value": "Koneoppimisty\u00f6kalujen toimintaperiaatteet", "language": "", "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "bachelor thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202306013436", "language": "", "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Bachelor's thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Kandidaatinty\u00f6", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Informaatioteknologia", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Information Technology", "language": "en", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Tietoj\u00e4rjestelm\u00e4tiede", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Information Systems Science", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "yvv.contractresearch.funding", "value": "0", "language": "", "element": "contractresearch", "qualifier": "funding", "schema": "yvv"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_7a1f", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "bachelorThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "601", "language": "", "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "teko\u00e4ly", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "neuroverkot", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "koneoppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "algoritmit", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}]
|