Methods and applications for computational neurosciences
A.A. 2023/2024
Obiettivi formativi
The Course aims to provide information on modern techniques of artificial intelligence and machine learning in medicine. The students will acquire the ability to define artificial intelligence and machine learning, to describe the potential role of artificial intelligence in medicine, to explain at a basic level why data type and quality is important for use in machine learning tools, and to identify the potential use of these methods for both experimental and clinical purposes.
Risultati apprendimento attesi
At the end of the Course, the students will achieve the following leaning outcomes:
1. Come into the methodological aspects related to the techniques of artificial intelligence and machine learning
2. Describe the learning process of neural networks
3. Interpret, with an active attitude to the themes, methods of supervised or unsupervised Learning
1. Come into the methodological aspects related to the techniques of artificial intelligence and machine learning
2. Describe the learning process of neural networks
3. Interpret, with an active attitude to the themes, methods of supervised or unsupervised Learning
Periodo: Secondo semestre
Modalità di valutazione: Esame
Giudizio di valutazione: voto verbalizzato in trentesimi
Corso singolo
Questo insegnamento non può essere seguito come corso singolo. Puoi trovare gli insegnamenti disponibili consultando il catalogo corsi singoli.
Programma e organizzazione didattica
Edizione unica
Responsabile
Programma
Introduzione all'Intelligenza Artificiale e all'apprendimento automatico. Apprendimento supervisionato e non supervisionato. Intelligenza Artificiale nella diagnosi e monitoraggio dei pazienti. Tecniche di elaborazione dei linguaggi. Analisi dei dati in medicina e cura della salute. Interpretabilità degli algoritmi di apprendimento automatico. Intelligenza Artificiale e analisi del rischio. Intelligenza artificiale e management degli ospedali.
Prerequisiti
Conoscenze di base in matematica e statistica.
Metodi didattici
I metodi didattici includono lezioni in presenza, esercitazioni, lavori di gruppo su casi studio e articoli scientifici.
Materiale di riferimento
Lecture notes and slides.
Repetto, M., La Torre, D., Federated Multicriteria Learning: A Goal Programming Perspective, 2022 International Conference on Decision Aid Sciences and Applications (DASA), 2022, 790-794.
Repetto, M., La Torre, D., Making It Simple? Training Deep Learning Models Toward Simplicity, 2022 International Conference on Decision Aid Sciences and Applications (DASA), 2022, 784-789.
Triberti, S., Durosini, I., Lin, J., La Torre, D., Ruiz Galán, M. On the "Human" in Human-Artificial Intelligence Interaction. Front Psychol. 2021;12:808995. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8738165/
Brownlee, J., How to use Learning Curves to Diagnose Machine Learning Model Performance, https://machinelearningmastery.com/learning-curves-for-diagnosing-machine-learning-model-performance/
Matheny, M.E., Whicher, D., & Israni, S. T. (2020). Artificial Intelligence in Health Care: A report from the National Academy of Medicine. Jama, 323(6), 509-510. https://jamanetwork.com/journals/jama/fullarticle/2757958
Persons, T.M., U. Artificial Intelligence in Health Care: Benefits and Challenges of Machine Learning in Drug Development. https://www.gao.gov/products/GAO-20-215SP
Matheny, M.E., Whicher, D., & Israni, S. T. (2020). Artificial Intelligence in HealthCare: A report from the National Academy of Medicine. Jama, 323(6), 509-510. https://jamanetwork.com/journals/jama/fullarticle/2757958
Alvarez-Melis, David and Tommi S. Jaakkola. "A Causal Framework for Explaining the Predictions of Black-Box Sequence-to-Sequence Models." ArXiv:1707.01943, November 14, 2017. http://arxiv.org/abs/1707.01943
Athalye, Anish, Logan Engstrom, Andrew Ilyas, and Kevin Kwok. "Synthesizing Robust Adversarial Examples." Last modified June 7, 2018. http://arxiv.org/abs/1707.07397
Bahl, Manisha, Regina Barzilay, Adam B. Yedidia, Nicholas J. Locascio, Lili Yu, and Constance D. Lehman. 2018. "High-Risk Breast Lesions: A Machine Learning Model to Predict Pathologic Upgrade and Reduce Unnecessary Surgical Excision." Radiology 286, no. 3: 810-818. https://doi.org/10.1148/radiol.2017170549
Ganin, Yaroslav, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. "Domain-Adversarial Training of Neural Networks." Last modified May 26, 2016. https://arxiv.org/abs/1505.07818
Yala, Adam, Regina Barzilay, Laura Salama, Molly Griffin, Grace Sollender, Aditya Bardia, Constance Lehman, et al. 2017. "Using Machine Learning to Parse Breast Pathology Reports." Breast Cancer Research and Treatment 161: 203-211. https://doi.org/10.1007/s10549-016-4035-1
Kabelac, Zachary, Christopher G. Tarolli, Christopher Snyder, Blake Feldman, Alistair Glidden, Chen-Yu Hsu, Rumen Hristov, E. Ray Dorsey, and Dina Katabi. "Passive Monitoring at Home: A Pilot Study in Parkinson Disease." Digital Biomarkers 3, no. 1 (April 30, 2019): 22-30. https://doi.org/10.1159/000498922
https://www.healthcareitnews.com/news/new-ai-diagnostic-tool-knows-when-defer-human-mit-researchers-say.
https://monkeylearn.com/blog/natural-language-processing-applications/
https://analyticsindiamag.com/10-nlp-open-source-datasets-to-start-your-first-nlp-project/.
Repetto, M., La Torre, D., Federated Multicriteria Learning: A Goal Programming Perspective, 2022 International Conference on Decision Aid Sciences and Applications (DASA), 2022, 790-794.
Repetto, M., La Torre, D., Making It Simple? Training Deep Learning Models Toward Simplicity, 2022 International Conference on Decision Aid Sciences and Applications (DASA), 2022, 784-789.
Triberti, S., Durosini, I., Lin, J., La Torre, D., Ruiz Galán, M. On the "Human" in Human-Artificial Intelligence Interaction. Front Psychol. 2021;12:808995. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8738165/
Brownlee, J., How to use Learning Curves to Diagnose Machine Learning Model Performance, https://machinelearningmastery.com/learning-curves-for-diagnosing-machine-learning-model-performance/
Matheny, M.E., Whicher, D., & Israni, S. T. (2020). Artificial Intelligence in Health Care: A report from the National Academy of Medicine. Jama, 323(6), 509-510. https://jamanetwork.com/journals/jama/fullarticle/2757958
Persons, T.M., U. Artificial Intelligence in Health Care: Benefits and Challenges of Machine Learning in Drug Development. https://www.gao.gov/products/GAO-20-215SP
Matheny, M.E., Whicher, D., & Israni, S. T. (2020). Artificial Intelligence in HealthCare: A report from the National Academy of Medicine. Jama, 323(6), 509-510. https://jamanetwork.com/journals/jama/fullarticle/2757958
Alvarez-Melis, David and Tommi S. Jaakkola. "A Causal Framework for Explaining the Predictions of Black-Box Sequence-to-Sequence Models." ArXiv:1707.01943, November 14, 2017. http://arxiv.org/abs/1707.01943
Athalye, Anish, Logan Engstrom, Andrew Ilyas, and Kevin Kwok. "Synthesizing Robust Adversarial Examples." Last modified June 7, 2018. http://arxiv.org/abs/1707.07397
Bahl, Manisha, Regina Barzilay, Adam B. Yedidia, Nicholas J. Locascio, Lili Yu, and Constance D. Lehman. 2018. "High-Risk Breast Lesions: A Machine Learning Model to Predict Pathologic Upgrade and Reduce Unnecessary Surgical Excision." Radiology 286, no. 3: 810-818. https://doi.org/10.1148/radiol.2017170549
Ganin, Yaroslav, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. "Domain-Adversarial Training of Neural Networks." Last modified May 26, 2016. https://arxiv.org/abs/1505.07818
Yala, Adam, Regina Barzilay, Laura Salama, Molly Griffin, Grace Sollender, Aditya Bardia, Constance Lehman, et al. 2017. "Using Machine Learning to Parse Breast Pathology Reports." Breast Cancer Research and Treatment 161: 203-211. https://doi.org/10.1007/s10549-016-4035-1
Kabelac, Zachary, Christopher G. Tarolli, Christopher Snyder, Blake Feldman, Alistair Glidden, Chen-Yu Hsu, Rumen Hristov, E. Ray Dorsey, and Dina Katabi. "Passive Monitoring at Home: A Pilot Study in Parkinson Disease." Digital Biomarkers 3, no. 1 (April 30, 2019): 22-30. https://doi.org/10.1159/000498922
https://www.healthcareitnews.com/news/new-ai-diagnostic-tool-knows-when-defer-human-mit-researchers-say.
https://monkeylearn.com/blog/natural-language-processing-applications/
https://analyticsindiamag.com/10-nlp-open-source-datasets-to-start-your-first-nlp-project/.
Modalità di verifica dell’apprendimento e criteri di valutazione
La valutazione (per studenti frequentanti) si base su attività svolte in classe (presentazioni di gruppo) e un esame finale a risposta multiple. Per studenti frequentanti, invece, la valutazione è basata su un esame scritto con domande aperte e a risposta multipla.
Siti didattici
Docente/i