|
Course unit
ARTIFICIAL INTELLIGENCE
PSP5070139, A.A. 2019/20
Information concerning the students who enrolled in A.Y. 2018/19
ECTS: details
Type |
Scientific-Disciplinary Sector |
Credits allocated |
Educational activities in elective or integrative disciplines |
M-PSI/01 |
General Psychology |
6.0 |
Course unit organization
Period |
First semester |
Year |
2nd Year |
Teaching method |
frontal |
Type of hours |
Credits |
Teaching hours |
Hours of Individual study |
Shifts |
Lecture |
6.0 |
42 |
108.0 |
No turn |
Examination board
Board |
From |
To |
Members of the board |
4 2019 |
01/10/2019 |
30/09/2020 |
ZORZI
MARCO
(Presidente)
CUTINI
SIMONE
(Membro Effettivo)
TESTOLIN
ALBERTO
(Membro Effettivo)
|
Prerequisites:
|
Basic knowledge of mathematics (high school level), including notions of linear algebra, calculus, and probability. Knowledge of statistics (“Statistical methods in psychology”) and neuroscience ("Brain and behaviour") are useful for better unserstanding some of the topics discussed in the course. Computer literacy is required for the lab practices. |
Target skills and knowledge:
|
The course presents the theoretical and computational foundations of brain-inspired artificial intelligence. The focus is on machine learning based on artificial neural networks and how this approach is used in cognitive (neuro)science for modeling perception and cognition. Laboratory classes will also introduce students to simple computer simulations with artificial neural networks. |
Examination methods:
|
Type of exam: written (exam time: 1 hour).
Modality: multiple choice questions (max 20 points) + open questions (max 6 points) + paper assignment (max 6 points).
Paper assignment: Each student will be required to write a 3/4-page essay that will be assigned during the course and that must be hand over on the day of the written exam. |
Assessment criteria:
|
The evaluation is based on the understanding of course topics and on the acquisition of the proposed concepts and methodologies. |
Course unit contents:
|
Introduction to artificial intelligence and machine learning. Artificial neural networks: mathematical formalism and general principles. Supervised learning: perceptron, delta rule, multi-layered networks and error backpropagation. Generalization and overfitting. Partially recurrent networks: learning sequential data. Unsupervised learning: associative memories and Hopfield networks, competitive learning, latent variable models, annealing, Boltzmann machines. Deep learning. Reinforcement learning. Computer simulation as a research method in cognitive (neuro)science. Connectionist models of perception and cognition. |
Planned learning activities and teaching methods:
|
Teaching is based on frontal lectures presenting the theoretical concepts, which will be also informally discussed to promote understanding through examples. The course includes lab practices (in a computer room) to explore computer simulations of artificial neural networks. |
Additional notes about suggested reading:
|
All study material will be available on the course Moodle (https://elearning.unipd.it/dpg/):
* Slides of the lectures
* Selected book chapters:
- G. Houghton, “Connectionist Models in Cognitive Psychology” (2005), Chapter 1
- D. Rumelhart and J. McClelland, “The PDP book” (1986), Chapter 1
- J. Anderson, “An Introduction to Neural Networks”, Chapter 12
* Selected articles:
- Elman, “Finding structure in time.” Cognitive Science (1990)
- Jacobs, and Grainger. "Models of visual word recognition: Sampling the state of the art." Journal of Experimental Psychology: Human perception and performance (1994)
- Zorzi, Testolin, and Stoianov. "Modeling language and cognition with deep unsupervised learning: a tutorial overview." Frontiers in Psychology (2013) |
Textbooks (and optional supplementary readings) |
|
Innovative teaching methods: Teaching and learning strategies
- Lecturing
- Laboratory
- Problem based learning
- Case study
- Use of online videos
- Loading of files and pages (web pages, Moodle, ...)
Innovative teaching methods: Software or applications used
- Moodle (files, quizzes, workshops, ...)
- Matlab
Sustainable Development Goals (SDGs)
|
|