Umjetne neuronske mreže izgrađene pomoću algoritma podizanja gradijenta

master's thesis

• Title (english): Gradient Boosting Neural Networks
• Author: Ivan Glavinović
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Committee member: Mirko Poljak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Umjetne neuronske mreže izgrađene pomoću algoritma podizanja gradijenta
Princip izgradnje ansambala neuronskih mreža pomoću algoritma podizanja gradijenta i usporedba performansi takvih rješenja s postojećim rješenjima gradijentno podignutih stabala odluka.

Abstract (english)

Neuron networks built using the gradient boosting algorithm.
The principle behind the building of ansambles of neuron networks using the gradient boosting algorithm and comparison of performance of such ansamble against existing gradient boosted decision tree algorithms.

• Keywords: Gradijentno podizanje; stabla odluka; neuronske mreže; XGBoost; LightGBM; GrowNet
• Keywords (english): Gradient boosting; decision trees; neural networks; XGBoost; LightGBM; GrowNet
• Language: croatian
• URN:NBN: urn:nbn:hr:168:246319
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 12:19:15