51. Detecting surface anomalies with deep learningDomen Rački, 2022, doktorska disertacija Ključne besede: Surface defect detection, visual inspection, quality control, solid oral dosage forms, pharmaceutical industry, deep learning, segmentation, convolutional neural networks, visual anomaly detection Celotno besedilo (datoteka, 11,17 MB) |
52. Characterization of biocomposites and glass fiber epoxy composites based on acoustic emission signals, deep feature extraction, and machine learningTomaž Kek, Primož Potočnik, Martin Misson, Zoran Bergant, Mario Sorgente, Edvard Govekar, Roman Šturm, 2022, izvirni znanstveni članek Ključne besede: polymer composites, biocomposites, GFE composites, acoustic emission, deep feature extraction, convolutional autoencoder, machine learning, neural networks Celotno besedilo (datoteka, 1,45 MB) Gradivo ima več datotek! Več... |
|
54. Cross-lingual word embeddings for knowledge transfer in less-represented languagesTadej Škvorc, 2022, doktorska disertacija Ključne besede: natural language processing, deep learning, neural networks, machine learning, text embeddings, knowledge transfer, idiom detection, conference scheduling, multilingual embeddings, contextual embeddings Celotno besedilo (datoteka, 1,21 MB) |
55. Predicting Bitcoin’s volatilityJan Pristovnik, 2022, magistrsko delo/naloga Ključne besede: volatility, forecasting, time series, cryptocurrency, time-series analysis, machine learning, recurrent neural networks, LSTM Celotno besedilo (datoteka, 10,26 MB) |
56. Deep learning in neuroimaging data analysisLev Kiar Avberšek, Grega Repovš, 2022, izvirni znanstveni članek Ključne besede: artificial intelligence, machine learning, deep learning, neuroimaging, neuroscience, data analysis, computational models, cognitive processes, learning, neural networks Celotno besedilo (datoteka, 2,23 MB) Gradivo ima več datotek! Več... |
|
58. Quantifying complex influences of chemical composition and soaking conditions for increasing the hot workability of M2 high-speed steel by using the alternative approachIztok Peruš, Heinz Palkowski, Goran Kugler, Milan Terčelj, 2020, izvirni znanstveni članek Ključne besede: M2 HSS, hot workability, hot compression, hot torsion, chemical compositions, Latin Hypercube Sampling, neural networks Celotno besedilo (datoteka, 3,05 MB) Gradivo ima več datotek! Več... |
59. To BAN or not to BANKristian Miok, Blaž Škrlj, Daniela Zaharie, Marko Robnik Šikonja, 2022, izvirni znanstveni članek Ključne besede: natural language processing, machine learning, transformer neural networks, Bayesian neural networks, BERT models, prediction uncertainty, reliability estimation, Monte Carlo dropout, Bayesian BERT, sentic computing, model calibration Celotno besedilo (datoteka, 3,06 MB) Gradivo ima več datotek! Več... |
60. Reconstructing superquadrics from intensity and color imagesDarian Tomašević, Peter Peer, Franc Solina, Aleš Jaklič, Vitomir Štruc, 2022, izvirni znanstveni članek Ključne besede: superquadrics, reconstruction, color images, deep learning, convolutional neural networks Celotno besedilo (datoteka, 17,96 MB) Gradivo ima več datotek! Več... |