Michelucci Umberto HSLU I

Dr. Umberto Michelucci Umberto Michelucci - PhD, PGCPSE (Open)

Lecturer

Michelucci Umberto HSLU I

Lucerne School of Computer Science and Information Technology

Room 8. Stock, shared
Campus Zug-Rotkreuz
Suurstoffi 1
6343 Rotkreuz


Continuing Education

Lecturer

+41 79 396 74 06

+41 79 396 74 06

Show email

Biography

Umberto Michelucci studied Theoretical Physics in Italy, the United States, Germany and England, focusing on simulations and the theory of high temperature superconductors. He obtained his PhD in Machine Learning applied to Physics from the Portsmouth University in England. He worked in various industries for many years, gaining industrial experience in various fields. He also founded and directed the AI Center of Excellence at Helsana Versicherung AG in Zürich. He is also the co-founder of the company TOELT LLC, that focuses on large international research project with a strong AI component. He is working often with Google and NVIDIA on various project. He has many years of teaching at various levels, Bachelor, Master, PhD and for continuing education. He also holds a Postgraduate Certificate in Higher Education.

He has written four books on Deep Learning with Springer Nature. His fourth, “Mathematical Concepts for Machine Learning in Science” just came out beginning 2024.

Associations / Membershipts

  • IEEE Member
  • IEEE Computational Intelligence Society Member

 

Education

  • PhD in Machine Learning applied to Physics
  • Master in Theoretical Physics
  • Postgraduate Certificate in Higher Education

 

Awards

 

Interviews

Subjects
  • CAS Artificial Intelligence
  • CAS Data Engineering and Applied Data Science
  • Computer Vision
  • Mathematics and Statistics
  • Deep Learning
Professional competencies
  • Applied Machine Learning and Deep Learning
  • Mathematics and Statistics
  • Programming in R and Python
  • Data Science
  • Lecturer of Mathematics and Physics
  • Mentoring MA-Thesis (Research Thesis und Design Project)
  • Mentoring von Studierenden und Doktorierenden in formellen und informellen Settings
  • Begleitung von Strategieentwicklungen, Innovationsprozessen
Teaching and research focus
  • Applied Machine Learning and Deep Learning
  • Image Processing & Computer Vision
  • Mathematics and Statistics
  • High performance computing and GPU programming
  • Programming in R and Python

Co-Leiter CAS Machine Learning, Data Engineering and Applied Data Science and Lecturer

Publications and presentations

Publications and presentations - Book/catalogue

  • Michelucci, Umberto (2022). Applied Deep Learning with TensorFlow 2: Learn to Implement Advanced Deep Learning Techniques with Python. Berkeley, CA: Apress.
  • Michelucci, Umberto (2019). Advanced applied deep learning: convolutional neural networks and object detection. New York: Apress.
  • Michelucci, Umberto (2018). Applied Deep Learning- A Case-Based Approach to Understanding Deep Neural Networks. New York: Springer nature.

Publications and presentations - Article, review; peer reviewed

  • Venturini, Francesca; Fluri, silvan & Michelucci, Umberto (2024). Shedding light on the ageing of extra virgin olive oil: Probing the impact of temperature with fluorescence spectroscopy and machine learning techniques. LWT - Food Science and Technology (Formerly: Lebensmittel-Wissenschaft und -Technologie), 2024, 1-1.
  • Schmid, Christian; Laurenzi, Emanuele; Michelucci, Umberto & Francesca, Venturini (2023). Explainable AI for the olive oil industry. International Conference on Business Informatics Research, 2023, 1-1.
  • Michelucci, Umberto & Venturini, Francesca (2023). New metric formulas that include measurement errors in machine learning for natural sciences. Expert Systems with Applications, 2023, 1. doi: https://doi.org/10.1016/j.eswa.2023.120013
  • Michelucci, Umberto (2023). Understanding the learning mechanism of convolutional neural networks applied to fluorescence spectra. AI and Optical Data Sciences IV, 2023, 178-184.
  • Michelucci, Umberto (2023). Deep learning super resolution for high-speed excitation emission matrix measurements. AI and Optical Data Sciences IV, 2023, 127-137.
  • Michelucci, Umberto (2023). Extraction of physicochemical properties from the fluorescence spectrum with 1D convolutional neural networks: Application to olive oil. Journal of Food Engineering, 2023, 336.
  • Michelucci, Umberto & Venturini, Francesca (2022). New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciences. Expert Systems with Applications, 2022, 1. doi: 10.48550/ARXIV.2209.15588
  • Venturini, Francesca; Michelucci, Umberto; Sperti, Michela; Gucciardi, Arnaud; Martose, Vanessa M. & Deriu, Marco A. (2022). Physico-chemical properties extraction from the fluorescence spectrum with 1D-convolutional neural networks: application to olive oil. Journal of Food Engineering, 2022, 336. doi: 10.48550/ARXIV.2203.07229
  • Arnaud, Gucciardi; Michelucci, Umberto; Venturini, Francesca; Sperti, Michela & Deriu, Marco Agostino (2022). Compact optical fluorescence sensor for food quality control using artificial neural networks: application to olive oil. Optical Sensing and Detection VII, 2022, 80. doi: 10.1117/12.2621588
  • Milleville, Kenzo; Thirukokaranam Chandrasekar, Krishna Kumar; Blyau, Thibault; Michelucci, Umberto; Iannello, AURORA & Verstockt, Steven (2022). Extraction and classification of historical stamp cards using computer vision. DH Benelux 2022-ReMIX: Creation and alteration in DH (hybrid), 2022, 1–4.
  • Sperti, Michela; Michelucci, Umberto; Venturini, Francesca; Gucciardi, Arnaud & Deriu, Marco Agostino . (2022). Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks. Optical Sensing and Detection VII, 2022, 81. doi: 10.1117/12.2621666
  • Venturini, Francesca; Michelucci, Umberto; Sperti, Michela; Gucciardi, Arnaud & Deriu, Marco Agostino (2022). One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge: explainability techniques applied to olive oil fluorescence spectra. Optical Sensing and Detection VII, 2022, 60. doi: 10.1117/12.2621646
  • Venturini, Francesca; Baumgartner, Michael & Michelucci, Umberto (2021). Implementation of multi-task learning neural network architectures for robust industrial optical sensing. Optical Measurement Systems for Industrial Inspection XII, 2021, 90. doi: 10.1117/12.2593469
  • Venturini, Francesca & Michelucci, Umberto (2021). New Autonomous Intelligent Sensor Design Approach for Multiple Parameter Inference. 7th International Electronic Conference on Sensors and Applications, 2021, 96. doi: 10.3390/engproc2020002096
  • Venturini, Francesca; Baumgartner, Michael & Michelucci, Umberto (2021). New Approach for Temperature-Immune Oxygen Sensing based on Pt-TFPP. OSA Optical Sensors and Sensing Congress 2021 (AIS, FTS, HISE, SENSORS, ES), 2021, SW5H.2. doi: 10.1364/SENSORS.2021.SW5H.2
  • Venturini, Francesca; Sperti, Michela; Michelucci, Umberto; Herzig, Ivo; Baumgartner, Michael; Caballero, Josep Palau; Jimenez, Arturo & Deriu, Marco Agostino (2021). Exploration of Spanish Olive Oil Quality with a Miniaturized Low-Cost Fluorescence Sensor and Machine Learning Techniques. Foods, 2021(5), 1010. doi: 10.3390/foods10051010
  • Halasz, Geza; Sperti, Michela; Michelucci, Umberto; Villani, Matteo; Agostoni, Piergiuseppe; Biagi, Andrea; Rossi, Luca; Botti, Andrea; Mari, Chiara; Maccarini, Marco; Pura, Filippo; Roveda, Loris; Nardecchia, Alessia; Mottola, Emanuele; Nolli, Massimo; Salvioni, Elisabetta; Mapelli, Massimo; Deriu, Marco Agostino; Piga, Dario & Piepoli, Massimo (2021). A Machine Learning Approach for Mortality Prediction in COVID-19 Pneumonia: Development and Evaluation of the Piacenza Score. Journal of Medical Internet Research, 2021(5), e29058. doi: 10.2196/29058
  • Michelucci, Umberto; Sperti, Michela; Piga, Dario; Venturini, Francesca & Deriu, Marco A. (2021). A Model-Agnostic Algorithm for Bayes Error Determination in Binary Classification. Algorithms, 2021(11), 301. doi: 10.3390/a14110301
  • D'Ascenzo, Fabrizio; De Filippo, Ovidio; Gallone, Guglielmo; Mittone, Gianluca; Deriu, Marco Agostino; Iannaccone, Mario; Ariza-Solé, Albert; Liebetrau, Christoph; Manzano-Fernández, Sergio; Quadri, Giorgio; Kinnaird, Tim; Campo, Gianluca; Simao Henriques, Jose Paulo; Hughes, James M; Dominguez-Rodriguez, Alberto; Aldinucci, Marco; Morbiducci, Umberto; Patti, Giuseppe; Raposeiras-Roubin, Sergio; Abu-Assi, Emad; De Ferrari, Gaetano Maria; Piroli, Francesco; Saglietto, Andrea; Conrotto, Federico; Omedé, Pierluigi; Montefusco, Antonio; Pennone, Mauro; Bruno, Francesco; Bocchino, Pier Paolo; Boccuzzi, Giacomo; Cerrato, Enrico; Varbella, Ferdinando; Sperti, Michela; Wilton, Stephen B.; Velicki, Lazar; Xanthopoulou, Ioanna; Cequier, Angel; Iniguez-Romo, Andres; Munoz Pousa, Isabel; Cespon Fernandez, Maria; Caneiro Queija, Berenice; Cobas-Paz, Rafael; Lopez-Cuenca, Angel; Garay, Alberto; Blanco, Pedro Flores; Rognoni, Andrea; Biondi Zoccai, Giuseppe; Biscaglia, Simone; Nunez-Gil, Ivan; Fujii, Toshiharu; Durante, Alessandro; Song, Xiantao; Kawaji, Tetsuma; Alexopoulos, Dimitrios; Huczek, Zenon; Gonzalez Juanatey, Jose Ramon; Nie, Shao-Ping; Kawashiri, Masa-aki; Colonnelli, Iacopo; Cantalupo, Barbara; Esposito, Roberto; Leonardi, Sergio; Grosso Marra, Walter; Chieffo, Alaide; Piga, Dario; Malavolta, Marta; Gili, Sebastiano; Mennuni, Marco; Montalto, Claudio; Oltrona Visconti, Luigi; Arfat, Yasir & Michelucci, Umberto (2021). Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets. The Lancet, 2021(10270), 199-207. doi: 10.1016/S0140-6736(20)32519-8
  • Venturini, Francesca; Baumgartner, Michael & Michelucci, Umberto (2020). Dual Oxygen and Temperature Luminescence Learning Sensor with Parallel Inference. Sensors, 2020(17), 4886. doi: 10.3390/s20174886
  • Venturini, Francesca; Baumgartner, Michael & Michelucci, Umberto (2020). Dual oxygen and temperature sensing with single indicator using multi-task-learning neural networks. Optical Sensing and Detection VI, 2020, 52. doi: 10.1117/12.2554941
  • Venturini, Francesca; Baumgartner, Michael & Michelucci, Umberto (2019). New approach for luminescence sensing based on machine learning. Optical Data Science II, 2019, 14. doi: 10.1117/12.2508969
  • Venturini, Francesca & Michelucci, Umberto (2019). Multi-Task Learning for Multi-Dimensional Regression: Application to Luminescence Sensing. Applied Sciences, 2019(22), 4748. doi: 10.3390/app9224748
  • Venturini, Francesca & Michelucci, Umberto (2017). Novel Algorithm for Calibration-Free Absorption Spectroscopy Sensor. Proceedings of the 5th International Symposium on Sensor Science (I3S 2017), 2017, 833. doi: 10.3390/proceedings1080833
  • Venturini, F.; Hackl, R.; Michelucci, U. & Michelucci, Umberto (2003). Comment on “Nonmonotonic d x 2 − y 2 Superconducting Order Parameter in N d 2 − x C e x C u O 4 ”. Physical Review Letters, 2003(14), 149701. doi: 10.1103/PhysRevLett.90.149701
  • Pimenov, A.; Pronin, A. V.; Loidl, A.; Michelucci, U.; Kampf, A. P.; Krasnosvobodtsev, S. I.; Nozdrin, V. S.; Rainer, D. & Michelucci, Umberto (2000). Anisotropic conductivity of Nd 1.85 Ce 0.15 CuO 4 − δ films at submillimeter wavelengths. Physical Review B, 2000(14), 9822-9826. doi: 10.1103/PhysRevB.62.9822
  • Michelucci, U.; Kampf, A. P.; Pimenov, A. & Michelucci, Umberto (2000). Anisotropic conductivity in superconducting NCCO. arxiv Archive, 2000, 1. doi: 10.48550/ARXIV.COND-MAT/0010409
  • Venturini, F.; Michelucci, U.; Devereaux, T. P.; Kampf, A. P. & Michelucci, Umberto (2000). Collective Spin Fluctuation Mode and Raman Scattering in Superconducting Cuprates. Physical Review B, 2000(22), 15204-15207. doi: 10.1103/PhysRevB.62.15204

Publications and presentations - Article, review; not peer reviewed

  • Venturini, Francesca; Michelucci, Umberto; Sperti, Michela; Gucciardi, Arnaud; Martos, Vanessa M. & Deriu, Marco A. (2023). Dataset of Fluorescence Spectra and Chemical Parameters of Olive Oils. arxiv Archive, 2023, 1. doi: 10.48550/ARXIV.2301.04471
  • Michelucci, Umberto (2023). On the High Symmetry of Neural Network Functions. arXiv preprint, 2023,
  • Michelucci, Umberto (2022). On the High Symmetry of Neural Network Functions. arxiv Archive, 2022, 1. doi: 10.48550/ARXIV.2211.06603
  • Michelucci, Umberto (2022). An Introduction to Autoencoders. arxiv Archive, 2022, 1. doi: 10.48550/ARXIV.2201.03898
  • Michelucci, Umberto & Venturini, Francesca (2021). Estimating Neural Network’s Performance with Bootstrap: A Tutorial. Machine Learning and Knowledge Extraction, 2021(2), 357-373. doi: 10.3390/make3020018
  • Venturini, Francesca; Baumgartner, Michael & Michelucci, Umberto (2019). Optical Oxygen Sensing with Artificial Intelligence. Sensors, 2019(4), 777. doi: 10.3390/s19040777

Publications and presentations - Theses (Bachelor/Master/Dissertation/Habilitation)

  • kalbermatten, diego & Michelucci, Umberto (2023). Smart Shelf – Führen der Inventur mithilfe Computer Vision & Deep Learning (nicht veröffentlichte Bachelorarbeit). HSLU, Schweiz.
  • Birbaumer, Mirko; Michelucci, Umberto & Schmid, Ralph (2022). IoT-based Attention Tracking in a Real-World Scenario (nicht veröffentlichte Master-/Lizentiats-/Diplomarbeit). HSLU Zentralschweiz, Schweiz.