Saúl Calderón and Manuel Zumbado participates in the Latin American event, Khipu 2023

Khipu is a non-profit organization with the purpose of supporting Latin American talent, research and companies, by holding events on Artificial Intelligence. In line with this objective, it promotes training in advanced machine learning topics, seeks to strengthen the scientific community and create opportunities for the exchange of knowledge, in order to raise awareness about the uses of AI for the benefit of Latin America.

Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images

In this work, is assessed the impact of the distribution mismatch between the labelled and the unlabelled datasets, for a semi supervised model trained with chest X-ray images, for COVID-19 detection. Under strong distribution mismatch conditions, was found an accuracy hit of almost 30%, suggesting that the unlabelled dataset distribution has a strong influence in the behavior of the model.
In this work, is assessed the impact of the distribution mismatch between the labelled and the unlabelled datasets, for a semi supervised model trained with chest X-ray images, for COVID-19 detection. Under strong distribution mismatch conditions, was found an accuracy hit of almost 30%, suggesting that the unlabelled dataset distribution has a strong influence in the behavior of the model.

Computer expert says Programmers need more math

Leslie Lamport revolutionized how computers talk to each other. Now he’s working on how engineers talk to their machines.
An American computer scientist who was awarded the 2013 Turing Award for explaining and formulating the behavior of distributed computing systems. Initial developer of the LaTeX text formatting system, and of BibTeX and creator of the Bakery Algorithm.

He thinks that is important to spend more time thinking about the solution and the algorithms than writing code, but unfortunately that is not taught in undergraduate computer science courses.

Ibaraky University

CARACTERÍSTICAS
Modalidad:
País:
Tipo:
Sector:
Fecha inicio y fin: Del al