The fourth edition of NOVA MATH - UNIDEMI Talks took place last June 28th, Wednesday, an event that aims to promote the sharing of knowledge and teamwork between the scientific areas of Mathematics and Industrial Engineering, through their respective Research Centers at NOVA School of Science and Technology | NOVA FCT.

At this fourth edition the speakers were: 
André Carvalho, Department of Mechanical and Industrial Engineering, UNIDEMI: Predictive quality: improving models to analyze, improve and automate value creation 
Abstract: As Artificial Intelligence hits the headlines with all-so-many uses across multiple sectors, many industrial applications are somewhat lagging behind, the promise of Industry 4.0 yet to fully materialize. The use of predictive analytics in Quality Engineering and Management is a prime example. While early promises of defect reduction and waste elimination generated great interest, most solutions proved to have high margins of error, as they are often based on one-size fits-all models. From existing models to new, more customized solutions, we will discuss opportunities for improved development of machine learning models for predictive analytics.
Rui Rodrigues, Department of Mathematics, NOVA MATH: Neural networks for time series
Abstract: In this presentation, we will showcase various applications of neural networks on time series data in the fields of cardiology and natural language processing. We will provide examples of how neural networks can be utilized for tasks such as classification, regression, and segmentation.
This seminar is funded by national funds through the FCT – Fundação para a Ciência e a Tecnologia, I.P., under the scope of the projects UIDB/00297/2020 and UIDP/00297/2020 (NOVA Math – Center for Mathematics and Applications), and UID/EMS/00667/2019 (UNIDEMI – Research and Development Unit for Mechanical and Industrial Engineering).