| Studiju veids |
bakalaura akadēmiskās studijas |
| Studiju programmas nosaukums |
Datorsistēmas |
| Nosaukums |
Normalizācijas funkciju salīdzinājums regresijas uzdevumos, izmantojot dziļo māšīnmācīšanos |
| Nosaukums angļu valodā |
Comparison of normalization functions in regression tasks using deep learning |
| Struktūrvienība |
12300 Lietišķo datorsistēmu institūts |
| Darba vadītājs |
Ēvalds Urtāns |
| Recenzents |
Marina Uhanova |
| Anotācija |
Normalization is a widely used method in deep learning field. It allows to
increase performance of the learning process, performed by neural networks. The
bachelor thesis consists of empirical analysis of 3 existing normalization functions.
Experiments were performed based on combination of different values of
hyperparameters, together with 3 datasets of different size and complexity with respect
to features (Weather in Szeged, CalCOFI, Stellar classification). Batch normalization
function “LayerNorm” has shown best performance on average among all of the
combination of experiments, while function “BatchNormLast” was classified as the
most unstable and had lowest performance.
The bachelor thesis contains: 59 pages, 34 figures and 26 referenced
information sources. |
| Atslēgas vārdi |
PADZIĻINĀTA MĀCĪŠANĀS, PARTIJU NORMALIZĀCIJA, REGRESIJA |
| Atslēgas vārdi angļu valodā |
DEEP LEARNING, BATCH NORMALIZATION, REGRESSION |
| Valoda |
eng |
| Gads |
2022 |
| Darba augšupielādes datums un laiks |
29.05.2022 15:52:46 |
