5 papers
Backpropagation-free Deep Learning for Time-Series Classification
Miha Kapš, Blaž Bertalanič, Carolina Fortuna
Deep neural networks for time series classification (TSC) are trained almost exclusively by error backpropagation, which imposes update locking and the weight-transport problem. Ba…
Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimation
Ljupcho Milosheski, Fedja Močnik, Mihael Mohorčič +1
Next-generation wireless systems such as 6G operate at higher frequency bands, making signal propagation highly sensitive to environmental factors such as buildings and vege- tatio…
Label-Free Concept Drift Assessment for Reliable AI in Emerging Wireless Applications
Athanasios Tziouvaras, Carolina Fortuna, George Floros +4
Machine learning models deployed in non-stationary environments degrade silently, since as the input distribution drifts their accuracy decays without an error signal and without l…
MRM3: Machine Readable ML Model Metadata
Andrej Čop, Blaž Bertalanič, Marko Grobelnik +1
As the complexity and number of machine learning (ML) models grows, well-documented ML models are essential for developers and companies to use or adapt them to their specific use…
A Network Science Approach to Granular Time Series Segmentation
Ivana Kesić, Carolina Fortuna, Mihael Mohorčič +1
Time series segmentation assigns a label to each part of a sequence. We formulate dense univariate segmentation as node classification on a graph whose nodes are the original time…