54 citations · 88 across the 13 of their papers we have counts for
3 papers · 1 filter
CNN-TFT explained by SHAP with multi-head attention weights for time series forecasting
Stefano F. Stefenon, João P. Matos-Carvalho, Valderi R. Q. Leithardt +1
Convolutional neural networks (CNNs) and transformer architectures offer strengths for modeling temporal data: CNNs excel at capturing local patterns and translational invariances,…
Time series forecasting based on optimized LLM for fault prediction in distribution power grid insulators
João Pedro Matos-Carvalho, Stefano Frizzo Stefenon, Valderi Reis Quietinho Leithardt +1
Surface contamination on electrical grid insulators leads to an increase in leakage current until an electrical discharge occurs, which can result in a power system shutdown. To mi…
A Closed-form Solution for Weight Optimization in Fully-connected Feed-forward Neural Networks
Slavisa Tomic, João Pedro Matos-Carvalho, Marko Beko
This work addresses weight optimization problem for fully-connected feed-forward neural networks. Unlike existing approaches that are based on back-propagation (BP) and chain rule…