The course aims at providing PhD Candidates knowledge on basic state of the art and advanced theories/techniques for learning from multisensory signals and data Bayesian models for jointly predicting, processing, filtering and interpreting observed interactions. Such models will be shown to enhance functionalities of embodied smart autonomous systems like cars, radios, drones, robots, buildings by providing them a self-awareness information basis. Networks of self-aware autonomous systems interacting in smart cognitive environment will be the also targeted as examples carried on in the course. From a methodological viewpoint, this module aims at identifying and describing methodologies and techniques for defining a common probabilistic framework suitable for:
- integrating contextual signals synchronously provided by multisensorial eso and endo sensors of autonomous systems by using Data Fusion paradigms and techniques;
- learning from experiences behavioural and causal self-awareness models allowing an autonomous system to describe the world through a vocabulary of normal locally stationary experiences;
- showing how each model learned from an experience can describe through probabilistic stationary rules dynamic perception, planning and actuation by means of collected external and internal observations.
Applications will be targeted of described techniques related to a couple of main case studies together with additional examples:
- self-awareness in autonomous ground and aerial vehicles and smart infrastructures (e.g. Buildings, dynamic radio spectrum)
- interactions in telecommunications scenarios like cognitive radio and internet of things.
- Data Fusion methodologies and techniques for integrating multisensorial contextual data Data Fusion models.
- JDL model and its extensions: signals, objects, situations, threats, processes and cognitive refinement.
- Coupled Dynamic Bayesian Networks.
- Bayesian multisensor state estimation and data association techniques:
- Continuous and discrete state estimation techniques: from Kalman filter to Particle Filters, Hidden Markov Models.
- PDAF and JPDAF.
- Switching models. Markov Jump and Rao Blackwellized filters.
- Learning methods from sparse and dense data
- Gaussian Processes, Generative Adversarial Networks, Variational Autoencoders.
- Unsupervised data dimensionality reduction: Self Organizing Maps, Growing Neural Gas, as semantic feature learning methods.
- Incremental learning: Dirichlet processes
- Techniques for non parametric self-awareness interaction-based predictive/generative/classification models .
- Bio-inspired neural basis of consciousness: Damasio model (core-self, protoself, autobiographical memory and autobiographical self)
- Applications and case studies:
- Cognitive radio and Internet of Things Physical anti-jammer securitySelf-awareness in autonomous ground and aerial vehicles
- Cognitive safety and physical security systems (smart patrolling in cooperative environments, preventive automotive vehicles, smart buildings, etc.)