OVERVIEW

This course aims at provining to the Master student basic and advanced concepts on the design of methods and techniques for data driven self-awareness in autonomous artificial agents . Signal Processing, Data Fusion and Machine learning under a Bayesian pespective will be the key dimensions on which introduced concepts will be described. Laboratory application and agent design will integrate course theoretical activities  

AIMS AND CONTENT

LEARNING OUTCOMES

The course aims at providing theory and techniques for architectural and functional design of interactive cognitive dynamic systems. Topics are related to data fusion, mutilevel bayesian state estimation and their application to cognitive video and radio domains. Project based learning allows students to acquire design capabilities in the field.

AIMS AND LEARNING OUTCOMES

  -Basic and advanced knowledge on design of telecommunication systems frameworks for context-aware multisensorial processing of signals and data in cognitive agents

- Knowledge on methods and techniques for acquisition, joint  representaion and processing of proprioreceptive and exteroreceptive  multisensorial signals in cognitive dynamic agents (e.g. semi autonomous&autonomous vehicles like drones, cars, robots) cognitive radios,   etc.) 

- Knowledge on methods and techniques for Multisensor Data Fusion: coupled hierarchical processing of multisensorial signals. Machine learning for data driven driven experience based learning of Dynamic Generative Fusion models from sequences of multdimensional sensorial data.

- Knowledge on Machine Learning methods and techniques based on Cognitive Dynamic Systems theory for Situation awareness and Self awareness in artificial cognitive agents 

- Knowledge and capabilities on case studies: design of Self Awareness frameowrk for autonomous systems (dataset on cars robots and drones, cognitive radios) 

- Knowledge and capabilities to use and apply: multisensorial signal processing tools and algorithms for acquisition,  experience driven machine learning techniques for estimation of Generative multisensorial Bayesian  hierarchical models. Bayesian Inference on learned Generative Models for dynamic state estimation, prediction and anomaly detection  of interaction between agent and its contextual environment situation .

PREREQUISITES

Probability theory, Random Processes, Signal theory 

TEACHING METHODS

Lessons for sharing knowledge 

Laboratory lessons to reinforce and assess capabilities 

SYLLABUS/CONTENT

• Cognitive Telecommunications Systems: an introduction 
• Signal Processing and Cognitive Systems: Bio inspired models
• Acquisition, representation and inference in Cognitive Dynamic systems 
• Data fusion architectural models 
• Data fusion levels and techniques 
  • Temporal and Spatial alignment
  • State estimation (Kalman filter,  Particle Filter, Switching models, Hierarchical filters)
  • Situation Awareness and Threat Assessment 
• Probabilistic Graphical Models and Dynamic Bayesian Networks 
  • Attractors and Bayesian inference
  • DBNs as experiences models 
    • ​Haykin model 
    • Damasio models
    • Friston model 
• Machine learning models for interaction modeling: 
  • Unsupervised and supervised clustering of big data
    • self Organizing Maps, Growing Neural Gas, Gaussian Processes, Dirichlet model
  • Mapping of learned models onto DBNs
  • Incremental learning of multiple models based on agent experiencesabnormal situations

Applying knowledge and understanding in lab 

• Basic language and tools inytroduction (matlab, C++, datasets used) I
• Case studies: autonomous car, lego robots, drones and simulators. 
• Applied Experiments using programming techniques and tools 
  • Filtering methods on data from dataset;
  • Single agent proprioreceptive and exteroceptive models 
  • Self awareness coupled interaction models.

Making Judgements:

• Interactive and Cognitive Systems project oriented techniques
  • Case study identification
  • Interaction system goal identification  (entities, service, evaluation performances)
  • State of the art description
  • Project design: architectural and technique level
  • Slide presentation
• Small team collaborative project definition; project management
• Individuating Emerging techniques in Cognitive Telecommunications domain

Learning and communications skills:

• Bibliographic search on scientific data bases (e.g. IEEEE Explore)

Conference style oral slide presentation 

RECOMMENDED READING/BIBLIOGRAPHY

- A. R. Damasio, Looking for Spinoza: Joy, Sorrow, and the Feeling Brain, 1st ed. Orlando: Harcourt, 2003. [Online]. Available:http://lccn.loc.gov/2002011347
- S. Haykin, Cognitive Dynamic Systems: Perception-action Cycle, Radar and Radio, ser. Cognitive Dynamic Systems: Perception–action Cycle, Radar, and Radio. Cambridge University Press, 2012.

- P. R. Lewis, M. Platzner, B. Rinner, J. Torresen, and X. Yao, Eds., Selfaware Computing Systems: An Engineering Approach. Springer, 2016.

 S. Haykin, Cognitive Dynamic Systems: Perception-action Cycle, Radar and Radio, ser. Cognitive Dynamic Systems: Perception–action Cycle, Radar, and Radio. Cambridge University Press, 2012.

- P. R. Lewis, M. Platzner, B. Rinner, J. Torresen, and X. Yao, Eds., Selfaware Computing Systems: An Engineering Approach. Springer, 2016.

- K. J. Friston, B. Sengupta, and G. Auletta, “Cognitive dynamics: From attractors to active inference,” Proceedings of the IEEE, vol. 102, no. 4, pp. 427–445, 2014. [Online]. Available:
https://doi.org/10.1109/JPROC.2014.2306251

- S. Haykin and J. M. Fuster, “On cognitive dynamic systems: Cognitive neuroscience and engineering learning from each other,” Proceedings of the IEEE, vol. 102, no. 3, pp. 608–628, 2014.

TEACHERS AND EXAM BOARD

Exam Board

CARLO REGAZZONI (President)

SILVANA DELLEPIANE

LUCIO MARCENARO

LESSONS

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

Project + Oral

ASSESSMENT METHODS

Project/Assigned dataset processing Report submission  plus oral project discussion

Project can be done either

- producing results using tools introduced in lessons and labs. A data set will be assigned describing a set of multisensorial signals acquired by an agent during a simulated or real experience. A report will have to be produced describing selected tools to allow agent to obtain a generative self awareness model allowing it anomaly detection on future experiences  

- considering a student selected application involving a agent and a CDS and producing a poster to discuss how course techniques can be applied on it 

Oral will consist in presenting and discussing slides related to the project by highlighting relationships and theoretical aspects of methods introduced in the course

Exam schedule

FURTHER INFORMATION

Dataset will be assigned at least two weeks before exam and report will have to be presented on Monday before exam date (usually on Thursday)  Oral admission will be communicated a day before oral exam.