25 citations · 26 across the 4 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Fractional Concepts in Neural Networks: Enhancing Activation Functions
Zahra Alijani, Vojtech Molek
Designing effective neural networks requires tuning architectural elements. This study integrates fractional calculus into neural networks by introducing fractional order derivativ…
cs.CV2023
Unproportional mosaicing
Vojtech Molek, Petr Hurtik, Pavel Vlasanek +1
Data shift is a gap between data distribution used for training and data distribution encountered in the real-world. Data augmentations help narrow the gap by generating new data s…