Search the digital library catalog

Query:	search in
	search in
	search in
	search in
Work type:	* old and bologna study programme
Language:
Search in:
Options:	Show only hits with full text
	Reset

1 - 3 / 3

NiaNetAD: Autoencoder architecture search for tabular anomaly detection powered by HPC
Sašo Pavlič, Sašo Karakatič, Iztok Fister, 2023, published scientific conference contribution

Keywords: predictive maintenance, autoencoder, anomaly detection, nature-inspired algorithms, optimization, high-performance computing, unsupervised learning
Published in DKUM: 26.01.2024; Views: 447; Downloads: 0

Construction of deep neutral networks using swarm intelligence to detect anomalies : master's thesis
Sašo Pavlič, 2021, master's thesis

Abstract: The design of neural network architecture is becoming more difficult as the complexity of the problems we tackle using machine learning increases. Many variables influence the performance of a neural model, and those variables are often limited by the researcher's prior knowledge and experience. In our master's thesis, we will focus on becoming familiar with evolutionary neural network design, anomaly detection techniques, and a deeper knowledge of autoencoders and their potential for application in unsupervised learning. Our practical objective will be to build a neural architecture search based on swarm intelligence, and construct an autoencoder architecture for anomaly detection in the MNIST dataset.
Keywords: neural architecture search, machine learning, swarm intelligence
Published in DKUM: 18.10.2021; Views: 1269; Downloads: 110
Full text (3,18 MB)
This document has many files! More...

Branje in obdelava signalov eeg - pristop s strojnim učenjem : diplomsko delo
Sašo Pavlič, 2019, undergraduate thesis

Abstract: Diplomska naloga zajema spoznavanje in predstavitev z osnovami EEG-možganskih valov s pomočjo naprave Emotiv Insight. Zajeti EEG-podatki predstavljajo vhodne podatke v modelu strojnega učenja, s pomočjo katerega se je ugotavljalo, kdaj in kje se pojavljajo iskani vzorci. Eksperiment razvite metode zajema podatkov in uporabe modela se je izvedel tako, da se je testni subjekt izpostavil izmenjujočim izbranim slikam, ob tem pa so se z napravo Emotiv Insight zajeli EEG-možganski valovi. Zajeti EEG-podatki so služili kot zbirka podatkov, iz katere se je učil klasifikacijski model umetne nevronske mreže, ki uspešno razpoznava, kdaj je testni subjekt podvržen eni vrsti slik in kdaj drugi.
Keywords: EEG, možganski valovi, strojno učenje, BCI-naprava, snemanje podatkov
Published in DKUM: 13.11.2019; Views: 1398; Downloads: 114
Full text (1,57 MB)

Search done in 0.07 sec.