diplomsko delo
Abstract
Diplomsko delo obravnava tematiko strojnega učenja s pomočjo uporabe umetnih nevron-
skih mrež. Te so po svojih sposobnostih in načinu delovanja zelo podobne delovanju
človeških možganov. Imajo sposobnost akumuliranja znanja s tako imenovanim postop-
kom ”učenja”, hkrati pa so sposobne to znanje tudi shranjevati.
Pravilnost delovanja mrež se s postopkom učenja, ki se ponavlja iterativno, povečuje.
Ena izmed glavnih težav pri učenju nevronskih mrež je pojav prekomernega prileganja,
ki se kaže v tem, da mreža ne posplošuje dobro iz učne na testno množico vzorcev. Za
preprečevanje tega pojava je bilo razvitih več tehnik, katerih uporaba, učinkovitost in
primerjava je predmet pričujočega diplomskega dela.
Keywords
umetne nevronske mreže;vzvratno razširjanje;prekomerno prileganje;regularizacija;diplomske naloge;
Data
Language: |
Slovenian |
Year of publishing: |
2017 |
Typology: |
2.11 - Undergraduate Thesis |
Organization: |
UM FERI - Faculty of Electrical Engineering and Computer Science |
Publisher: |
J. Henčič |
UDC: |
004.85.032.26(043.2) |
COBISS: |
20869142
|
Views: |
1111 |
Downloads: |
128 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
Overfitting prevention in training of multilayer neural networks |
Secondary abstract: |
This thesis deals with the subject of machine learning by using artificial neural networks.
They are very similar to the human brain in their abilities and way of functioning. They
have the capacity to accumulate knowledge through the so-called “learning” process, but
they are also able to store this knowledge.
The accuracy of artificial neural networks is increased in the process of learning,
which is repeated iteratively. One of the main problems in this process is the emergence
of overfitting. This is because the network does not generalize well from the learning
to the test set. To prevent this phenomenon several different techniques have been
developed, the application and effectiveness of which have been analyzed and compared
in the present thesis. |
Secondary keywords: |
artificial neural network;backpropagation;overfitting;regularization; |
URN: |
URN:SI:UM: |
Type (COBISS): |
Bachelor thesis/paper |
Thesis comment: |
Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije |
Pages: |
VIII, 29 f. |
ID: |
10859140 |