1. Home
  2. INTELLIGENT SYSTEMS

INTELLIGENT SYSTEMS

Degree course: 
Corso di Second cycle degree in COMPUTER SCIENCE
Academic year when starting the degree: 
2022/2023
Year: 
1
Academic year in which the course will be held: 
2022/2023
Course type: 
Compulsory subjects, characteristic of the class
Language: 
English
Credits: 
9
Period: 
First Semester
Standard lectures hours: 
72
Detail of lecture’s hours: 
Lesson (72 hours)
Requirements: 

The course assumes that students have a background acquired on a Bachelor's Degree in Computer Science. Specifically, students will be expected to be familiar with basic Vector and Matrix Calculation and Statistics.

Final Examination: 
Orale

The students’ learning extent is assessed via a written test (duration: 2 hours) and an individual assignment, autonomously developed by each student.

The goal of the written test is to assess the learning degree and the understanding of the elements related to intelligent systems from both theoretical and application (on problems of limited complexity) points of view. Written tests consist of:
- exercises for the assessment of the students’ understanding and knowledge of machine learning techniques
- questions on the conceptual aspects.

The assignment allows the students to use their skills and knowledge for the building of machine learners. The project presentation has the goal of assessing the students’ communication skills in two areas: 1) the students’ technical competencies and use of the correct terminology; 2) the student’s skills for communicating a complete and organized view of the work they carried out.
Individual judgment skills are evaluated based on the decisions made during the written exam and the assignment.
The grade of the written test (as well as the mid-term and final tests) is on a 0 to 30 scale. The written exam provides 70% of the final mark, while the assignment contributes the remaining 30%.

Assessment: 
Voto Finale

The course provides broad coverage of intelligent systems solving pattern recognition problems. Theoretical concepts in intelligent systems and techniques relevant to real-life applications will be illustrated.
The student will be able to:
1. Know the main objectives and areas of Artificial Intelligence, Machine Learning, and Pattern Recognition, with the ability to identify the potentialities of intelligent techniques and the relationships with other disciplines
2. Know the basic concepts of automated learning based on machine learning approaches and the conditions for their applicability
3. Know the most relevant feature extraction and selection techniques
4. Know statistical techniques and their limitations and strengths, with the ability to appropriately select the proper technique in specific contexts
5. Know basic principles of neural computing and their characteristics
6. Know Flat and Hierarchical Clustering with the ability to configure and apply these methods in specific contexts
7. Know performance metrics for learners
8. Know basic concepts of the following application domains: Image Classification, Text Categorization, Biomedical Data Analysis
9. Know how to program in a language for statistical computing and machine learning applications like R

It is also expected that students develop communicative skills through open discussion and autonomous assessment in the choice of the proper technique to solve problems of recognition and /or automatic classification of multidimensional data in several domains.
Students will acquire also knowledge of the relevant Machine learning and Pattern Recognition terminology.

The acquisition of knowledge and expected skills is developed along the entire course, which includes the topics listed below.

1)Introduction to Artificial Intelligence and Pattern Recognition: Historical Perspective, State of the Art of methods and applications (3h- Course Objective 1)

2) Design of a supervised classifier; Basic principles of learning by example; basic concepts of multidimensional pattern analysis (4 h- Course Objective 2)

3)Feature extraction and selection:
• Principal Component Analysis
• Information Gain
• Statistical evaluation of features
• Sequential Forward Selection,
• Design of Multidimensional Patterns in Text Classification, Image Recognition and in Content-Based Retrieval
(8h Course Objective 3)

4) Fundamental Elements of Programming with R
(8h- Course Objective 9)

5) Machine Learning Algorithms:
• Minimum distance classifier
• Deterministic distances
• Bayes’s rule
• Maximum likelihood classifier
• K-Nearest Neighborhood classifier
• Parallelepiped Method
• Decision trees
• Ensemble models: boosting, bagging, stacking
• Support Vector Machine
• Linear models, Polynomial basis function, Gaussian basis function and regularization.
• Frequent itemsets and association rules mining
• Regression models
• Hyperparameter tuning
• Performance metrics
• Examples of application of evaluation metrics in Image Classification, Medical Informatics and Information Retrieval domains
(34h- Course Objectives 2, 3, 4, 7)

6)Neural Networks
• Introduction, taxonomy
• Basic principle of neural computing
• Feedforward Neural Models
• Application Examples
• Introduction to Deep Learning techniques
(6h- Course Objective 5)

7) Clustering
• Introduction to Clustering
• K-means Clustering algorithm
• Agglomerative Hierarchical Clustering: Single linkage, Complete linkage
(5h- Course Objective 6)

8) Design of Intelligent Systems, Examples in application domains
(4h- Course Objectives 1, 8)

Convenzionale

Lectures (72 hours)

The topics of the course are illustrated by means of (1) conceptual, formal descriptions, (2) their implementation via R code, (3) and the use of demos and online resources.
Constant interaction with the students and their involvement in open discussions is highly encouraged.

During the period in which the course is held, the students can meet with the instructor on class days. During the remainder of the year, the students need to contact the instructor to set up an appointment (sandro.morasca@uninsubria.it). The instructor responds only to e-mail messages sent from the official student.uninsubria.it e-mail accounts.

Professors

MORASCA SANDRO

Borrowers