SCIENTIFIC PROGRAMMING

Single discipline educational activity

Course Sheet

Course code:

CH0006

Academic Year of enrolment:

2022

Year of supply:

2022/2023

Type of Course:

Characterising

Degree:

Course of 2nd Cycle Degree in COMPUTATIONAL COGNITIVE SCIENCE

Disciplinary Sector:

Data Processing Systems

Language:

Italian

Location:

CHIETI

Credits:

Programme Year:

Professor and Collaborators:

CAROPRESE Luciano

Cycle:

Second semester

Hours of classroom activity:

Individual study hours:

136

Prerequisites:

Good knowledge on mathematical analysis and geometry.

Objectives

The course aims to provide knowledge on programming languages and techniques, algorithms and data structures useful for scientific programming, and techniques for Machine Learning and Deep Learning.

Contents

The course aims to provide knowledge on programming languages and techniques, algorithms and data structures useful for scientific programming, and techniques for Machine Learning and Deep Learning.
The course will be structured into two modules. In the first module, information on computer structure and memory management will be provided. The basics of the Python programming language will then be introduced, and fundamental data structures will be covered. The use of functions, loops, and conditional statements will be illustrated. Object-oriented programming and recursive programming concepts will also be presented. Information will be provided for code management, data mining, and results visualization.
In the second module, fundamental concepts related to Machine Learning and Deep Learning will be presented. The main techniques for supervised and unsupervised Machine Learning and the necessary libraries for the development of regression and classification models will then be introduced. Finally, the main architectures of Deep Neural Networks and the libraries for their development will be presented.

Extended Syllabus

• General Information
• The Python Language
• Machine Learning
• Support Vector Machine
• k-Nearest Neighbors, Linear Regression, and Logistic Regression
• Decision Trees and Random Forest
• Unsupervised Learning
• Introduction to Artificial Neural Networks
• Convolutional Neural Networks
• Recurrent Neural Networks

Recommended Bibliography

Course books and slides will be suggested/made available by the teacher.

Methods of Provision

Conventional

Teaching Methods

The course consists of 64 hours of face-to-face teaching, divided into 2-hour lessons. The face-to-face lessons will be supported by slides and will cover the theoretical aspects of the discipline.
In addition, practical exercises are planned within the course. Attendance at the lessons is optional but highly recommended.
The slides and other teaching materials will be available on the e-learning platform of the course.

Evaluation methods

Verification of learning:

The learning assessment consists of two tests: the development of an individual project and an oral exam. In the project development, the student applies the concepts learned during the course. The project must be accompanied by a report that documents the activities carried out and the results obtained. The projects are agreed upon with the teacher.

The oral exam aims to evaluate the understanding of the technical and theoretical aspects of the concepts presented during the course. The final grade is expressed on a scale of thirty. In order for the final evaluation to be positive, the student must score at least 18 points.

Contacts/More Information

The slides and other didactic stuff will be available on the e-learning platform of the course.
Attendance at lectures is highly recommended.

Università degli Studi
"G. d'Annunzio"

Chieti - Pescara

Aree

Error message