Biography:
Jaime Pizarroso earned degrees in Industrial Engineering (specializing in Electronics), a Double Master's in Industrial Engineering and Connected Industry, and a PhD from Universidad Pontificia Comillas in 2017, 2019, and 2023, respectively. After completing his PhD, he joined the Department of Telematics and Computing as an Assistant Collaborating Professor, where he currently teaches undergraduate courses on machine learning, natural language processing, time series analysis, and deep learning. He balances his teaching duties with research projects at the Institute for Research in Technology (IIT), mainly on topics related to data analysis and applications of artificial intelligence.
Areas of interest:
Artificial Intelligence, Machine Learning, Explainable Artificial Intelligence.
Experience:
Jaime's professional journey includes significant roles such as an R&D Data Scientist at Nommon Solutions and Technologies, a Microelectronic Design Engineer at CRISA, and an Associate Researcher at the Institute for Research in Technology, IIT. His work has been marked by the application of predictive modelling, development of innovative products, and the implementation of machine learning and process diagnosis through data analysis. In addition to his professional pursuits, Jaime has contributed to the scientific community through his articles published in reputable journals. His work includes research on sensitivity analysis of neural networks and the analysis of input interactions in MLP models.
Skills:
- Languages: Spanish (nativo), English (C2), German (A2)
- Programming: Python, R, MATLAB, LaTeX
- Libraries and frameworks: TensorFlow, Pytorch, Keras, Shiny, Streamlit
- Software Development Tools: Git, SVN
- Software: Python, Matlab, RStudio, VS Code, Data Analysis, Machine Learning
Current research interests:
Artificial Intelligence, Machine Learning with Neural Networks, Explainable Artificial Intelligence.
Pizarroso, J., Portela, J., Muñoz, A., NeuralSens: sensitivity analysis of neural networks. Journal of Statistical Software. Vol. 102, nº. 7, pp. 1 - 36, April 2022. 
JCR: 5,800 Q1 (2022); 5,400 Q1 (2023) - SJR: 2,722 Q1 (2022); 2,709 Q1 (2023) 
