- Oggetto:
- Oggetto:
Advanced course: An introduction to machine learning for Neuroscience
- Oggetto:
Advanced course: An introduction to machine learning for Neuroscience
- Oggetto:
Academic year 2020/2021
- Teacher
- Andrea Cavallo (Lecturer)
- Year
- 1° anno, 2° anno, 3° anno, 4° anno
- Teaching period
- Primo semestre
- Type
- PhD Course
- Credits/Recognition
- 2
- Course disciplinary sector (SSD)
- ING-INF/06 - electronic and informatics bioengineering
- Delivery
- A distanza
- Language
- Italiano
- Attendance
- Facoltativa
- Oggetto:
Sommario del corso
- Oggetto:
Course objectives
Nowadays, machine learning is applied in almost every field. Machine learning relies entirely on the data; the more the data, the more efficient machine learning is. The ever-growing quantity of data in the neuroscience field opens the realm of possibilities for machine learning to learn a clinical task and answer the clinical-related hypothesis. However, what is the added value that machine learning brings to an ordinary statistical analysis? How machine learning can be exploited to find discriminative information encoded in the data? How machine learning can be exploited to localize where the discriminative information is placed? In this workshop, we will try to answer these questions by focusing on the design and the application of machine learning approaches in order to answer specific experimental and clinical questions. The workshop will take place on two different days. For each day a theoretical session about machine learning methodologies will be followed by an interactive laboratory where the participants will apply machine learning methodologies in their clinical and experimental dataset.
- Oggetto:
Results of learning outcomes
At the end of the course, students will have a preliminary knowledge of theoretical and practical aspects of machine learning. They will also be able to:
- Use the Statistics and Machine learning toolbox implemented in Matlab
- Perform feature selection and dimensionality reduction of multivariate datasets
- Apply basic machine learning techniques to their own data
- Compute statistical significance of machine learning results
- Oggetto:
Program
Course content:
(list of topic covered)
- Machine learning & Artificial Intelligence: Introduction
- Experimental question: Do my experimental conditions have discriminatory information?
- Matlab: Decision Tree, Linear Discriminant Analysis, Support Vector Machine
- Experimental question: Is the discriminatory information significant?
- Matlab: example of permutation test
- Experimental question: Which features/variables can best discriminate between my conditions?
- Matlab*: example of forward feature selection (wrapper approach), feature selection basata su fisher score e mutual information (filter approach)
- Oggetto:
Course delivery
Two days workshop – On-line
Suggested readings and bibliography
- Oggetto:
Notes
Teachers:
Luca Romeo – Università Poitecnica delle Marche - l.romeo@staff.univpm.it;
Andrea Cavallo – Università degli Studi di Torino - andrea.cavallo@unito.it;
Dates
19/02/2021
26/02/2021
Time
9:00-12:00
14:00-17:00
- Enroll
- Closed
- Enrollment closing date
- 26/02/2021 at 09:00
- Oggetto: