Intelligence for Embedded Systems – 2016/2017

MISSION AND GOALS

This course has been thought for Ph.D. and Master students willingly to learn, understand or perfect the fundamental mechanisms behind intelligence and how they can be used to design the future generation of embedded systems and embedded applications

SUBJECT AND PROGRAMME OF THE COURSE

The course presents the intelligent-based methodological and technical aspects making embedded systems and embedded applications able to deal with uncertainties and evolving environments. More specifically, the course addresses the following aspects:

  • From metrology to smart sensors (the measurement chain and its properties in smart sensing solutions)
  • Uncertainty, information and learning (intelligent solutions to deal with uncertainties at different levels: data acquisition, representing information, processing the information and learning mechanisms)
  • Robustness analysis and Probably Approximately Correct Computation (concepts)
  • Emotional cognitive mechanisms for embedded and cyber-physical systems
  • Adaptive mechanisms in embedded and cyber-physical systems systems (at the single unit and group level)
  • Learning in nonstationary and evolving environments (active and passive solutions)
  • Model-free Fault Detection and Diagnosis Systems in embedded and cyber-physical systems

INSTRUCTION LANGUAGE

English

SCHEDULE OF THE COURSE (updated)

Lesson – Schedule – Room – Time
1)   23/01/17   Seminari (DEIB)   13.15-16.15
2)   01/02/17  Seminari (DEIB)   13.15-16.15
3)   03/02/17   Seminari (DEIB)   13.15-16.15
4)   08/02/17   Seminari (DEIB)   13.15-16.15
5)   13/02/17   Seminari (DEIB)   13.15-16.15
6)   22/02/17   Conferenze (DEIB)   10.15-13.15
7)   27/02/17   Seminari (DEIB)   13.15-16.15
8)   03/03/17   Seminari (DEIB)   09.15-13.15

TEACHING ORGANIZATION

The aspects presented in the course are methodological (hence technology independent although technological implications will be given) and cross several disciplines (from measurements and metrology to machine learning and computer science in general).

TEACHING MATERIALS

Slides:

Lecture_1
Lecture_2
Lecture_3_Part_1
Lecture_3_Part_2
Lecture_4
Lecture_5

Matlab Demo Files:

Lecture_2
Lecture_3_Part1
Lecture_3_Part 2
Lecture_5

Additional materials

  • Reference book: “Intelligence for Embedded Systems: A Methodological Approach”, C. Alippi, Springer, 2014

LEARNING EVALUATION

Project/Thesis