Optional group:
curriculum Sistemi Informatici Complessi II ANNO -QUATTRO A SCELTA TRA - (show)
 |
24
|
|
|
|
|
|
|
|
|
20801798 -
INTELLIGENT SYSTEMS FOR THE INTERNET
(objectives)
The course will allow students to learn various methods for the design, implementation, and testing of adaptive systems on the Web, created through Artificial Intelligence techniques, with particular reference to Machine Learning techniques. Specific attention will be paid to Information Retrieval systems, such as search engines, crawlers and document feeds. Classic retrieval models will be studied, such as the Vector Space Model and probabilistic models, document ranking techniques, as well as the PageRank algorithm used by Google. Machine Learning methods in Information Retrieval will be addressed, including techniques for Sentiment Analysis, User Modeling methods necessary for personalized search, and social search applications involving communities of individuals in activities such as content tagging and question answering. The techniques for analyzing social networks (e.g., Facebook and Twitter) will be explored, which will allow us to explore phenomena such as the spread of fake news, the filter bubble, and the polarization of users. Finally, Recommender Systems will be studied, from basic algorithms (e.g., collaborative filtering) to application scenarios (e.g., movies, books, music artists and songs).
-
Derived from
20801798 SISTEMI INTELLIGENTI PER INTERNET in Ingegneria informatica LM-32 SANSONETTI GIUSEPPE
( syllabus)
The course will examine various methods for the design, implementation, and testing of adaptive systems on the Web, realized through Artificial Intelligence techniques. Particular attention will be paid to Information Retrieval systems, such as search engines, and to new and emerging technologies suitable for realizing the next generation of intelligent and personalized search tools. We will study classical retrieval models, such as the vector space model and probabilistic models, document ranking techniques, as well as the PageRank algorithm adopted by Google. Algorithms of Machine Learning in Information Retrieval will be addressed, including techniques for Sentiment Analysis, User Modeling methods needed for developing personalized research tools and recommender systems, identifying and analyzing online communities, and social networks (such as Facebook and Twitter).
( reference books)
Lectures will cover topics dealt with in scientific papers and reference texts.
The teacher will make available the slides from the lectures through the course website. Those slides will be self-contained, that is, written in such a way as not to require the consultation of further texts for passing the exam.
|
6
|
ING-INF/05
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
20810140 -
CYBERSECURITY
(objectives)
The Cybersecurity course intends to provide the student with competencies needed for understanding and tackling cybersecurity problems for ICT systems and complex organizations, to design networks and computing systems with a certain level of security, and to planning e manage activities related to cybersecurity. The course provides competences about attacks, countermeasures, cryptographic tools, applications, and methodologies in the cybersecurity field. Advanced topics in data integrity are also addressed.
-
PIZZONIA MAURIZIO
( syllabus)
• Course introduction
• Introduction to computer security and terminology
• Vulneability and threats
◦ Software vulnerabilities. Trusted and untrusted input, input validation. Vulnerabilities of applications written with interpreted languages, code injection. Injection into web pages: XSS. Cross site request forgery. OWASP.
▪ Example of web site that is vulnerable to sql injection
◦ buffer overflow attacks. Exploitation: privilege excalation, intrusions through opens services, intrusions through untrusted documents (email, web, etc).
▪ Example of vulnerable code, buffer overflow and related exploit
◦ Vulnerabilities of networks: sniffing, mac flood, ARP poisoning, vulnerability of DNS, Kaminsky attack. TCP session hijecking, MitM attack, DoS and Distributed DoS, Route hijacking.
• Security planning : security plan content, risk analysis.
• Countermeasures
◦ Design principles of policies and mechanisms.
◦ Models: AAA, confinement, DAC, MAC, access control matrix
◦ Cryptographic techniques:
▪ critptography basics (hash, symmetric c., asymmetric c., MAC, digital signature), birthday attack, rainbow, key quality, pseudo-random number generators.
▪ Authentication protocols and key exchange. replay and reflection attacks. Nonces. Perfect Forward Secrecy. Diffie-Helman.
▪ Certificates, certification authority, public key infrastructures and their vulnerabilities.
▪ Applications: Protocols ssl, tls, ssh, virtual private networks, ipsec, etc. Autnetication protocols wan and lan. radius and vulnerabilities. Other applications.
◦ Anomaly detection systems.
◦ System security:
▪ general principles: passwords and their vulnerabilities, hardening, assessment and auditing
▪ unix: discertionaly access control, file system security, authentication, PAM, syslog
◦ Network security:
▪ Firewalling:stateless and statefull firewall, connections, syn-proxy and syn-cookies, load balancing and high availability, linux netfilter and configuration examples.
▪ Network siecurity at level 1 and 2.
▪ Applicative proxies and network intrusion detection systems .
• Authenticated Data Structures
• Distributed Ledger Technologies and Bitcoin
• Smart contracts
• Cybersecurity in big organizations.
( reference books)
Course handouts
|
6
|
ING-INF/05
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
20810223 -
INGEGNERIA DEI DATI
(objectives)
Providing skills on systems, methods, and technologies for extraction, cleaning, analyzing and integrating and management of unstructured data.
-
MERIALDO PAOLO
( syllabus)
Source discovery
Data and Information Extraction
Data preparation
Data cleaning
Entity Resolution
Schema matching
Data fusion
Knowledge graphs
( reference books)
Slides and scientific papers provided by the teacher
|
6
|
ING-INF/05
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
20810261 -
Computer Graphics
(objectives)
This course aims at illustrating the modern software and hardware computer graphics architectures, and at providing mathematical, technical and methodological solutions for the development of projects concerning the visualization of data in 2D or 3D. The course will expose base concepts in computer graphics such as spaces, curves, surfaces and volumes, focusing on notions and algorithms currently used in scientific visualization, videogames, and computer animation. Moreover, this course aims at exposing details of hardware and software platforms currently in use.
-
MILICCHIO FRANCO
( syllabus)
OpenGL, Vulkan, OpenCL and CUDA; Mesh and Spatial Data Structures; View Pipeline; Curves and Surfaces; Ray Tracing; Meshing; Colors and Animations; Physics Based Animation.
( reference books)
- Online documentation for OpenGL, Vulkan, OpenCL, and CUDA;
- Introduction to Computer Graphics, by David J. Eck (free, online);
- MIT OpenCourseware "Computer Graphics", Lecture Notes (free, online);
|
6
|
ING-INF/05
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
20802136 -
CYBER PHYSICAL SYSTEMS
(objectives)
Building effective CPS of the future require multi-disciplinary skills. In particular, the confluence of real-time computing, wireless sensor networks, control theory, signal processing and embedded systems are required to create these new systems. This course will cover some basic material from these areas, but focus on advanced research papers related to CPS.
|
6
|
ING-INF/04
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
20810262 -
Deep Learning
(objectives)
Provide advanced and specific skills in Deep neural networks. The course consists of a theoretical part on the fundamental concepts, and laboratory activities in which these concepts are applied and developed through a software framework. At the end of the course the student will be able to: adequately train and optimize Deep neural networks; distinguish between different solutions and be able to choose and customize the most effective architectures in real-world scenarios, supervised, unsupervised or following a reinforcement learning approach.
-
GASPARETTI FABIO
( syllabus)
Introduction to DL; Training of Deep Architecture: hyperparameter tuning, batch normalization, faster optimizers, regularization ; Convolutional Neural Networks (CNN/ConvNets); Recurrent Neural Networks (GRU, LSTM, Bidirectional); Encoder-Decoder, Autoencoders, Variational Autoencoders; Attention layers ; Generative Adversarial Networks (GAN); Deep Reinforcement Learning; Embeddings; Use cases: AlexNet, VGG, NiN, GoogLeNet/Inception, ResNet, DenseNet; Use cases: Computer Vision and NLP
( reference books)
Hands-on machine learning with Scikit-learn Keras and TensorFlow by Aurelion Geron published by O` Reilley
Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville published by MIT Press
|
6
|
ING-INF/05
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
20810264 -
Pianificazione Automatica
(objectives)
The course presents Artificial Intelligence planning problems. It introduces models and resolution techniques for both "classic" and temporal planning, involving scheduling aspects. Different methodologies for the synthesis of action plans and their execution will be presented, as well as aspects related to automated learning of classical planning domains. Furthermore, some applications and samples will be presented and discussed, also in relation to the control of autonomous robots
-
ORLANDINI ANDREA
( syllabus)
- Basic concepts
- Modeling
- Solving approaches
- State-space planning
- Plan-space planning
- Planning graph
- Planning & Heuristics
- Planning with Control rules
- HTN Planning
- Temporal Planning
- Exercises with PDDL
( reference books)
- Slides of lectures
- Automated Planning: Theory and Practice. Ghallab, Nau, Traverso. Morgan Kaufmann Publishers, May 2004, 663 pages. ISBN 1-55860-856-7
|
6
|
ING-INF/05
|
54
|
-
|
-
|
-
|
Core compulsory activities
|
ITA |
|
Università Roma Tre