id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-159425-fgbruo9l	Paticchio, Alessandro	Semi-supervised Neural Networks solve an inverse problem for modeling Covid-19 spread	2020-10-10		.txt	text/plain	2530	146	55	This method consists of unsupervised and supervised parts and is capable of solving inverse problems formulated by DEs. We also propose an extension of the SIR model to include a passive compartment P , which is assumed to be uninvolved in the spread of the pandemic (SIRP), presenting a novel machine learning technique for solving inverse problems and improving disease modeling. Then, we introduce the SIRP model and study the pandemic's evolution by applying the semi-supervised approach to real data, capturing the populations infected and removed by COVID-19 in Switzerland, Spain, and Italy. We examined the effectiveness of the SIRP model and the semi-supervised method by fitting data obtained during the COVID-19 pandemic for three countries: Switzerland, Spain, and Italy [3] . We applied the proposed semi-supervised method on real data to study the COVID-19 spread in Switzerland, Spain, and Italy.	./cache/cord-159425-fgbruo9l.txt	./txt/cord-159425-fgbruo9l.txt