COGNITIVE COMPUTING AND ARTIFICIAL INTELLIGENCE

Note: This course is offered in English

The course provides an integrated and modern approach to the design and development of intelligent systems, by resorting to state of the art technologies and methods from the fields of machine learning, large-scale multimedia analysis, knowledge representation, natural computation, logic and automated reasoning to solve typical and topical problems in application scenarios such as: human-computer interaction, business intelligence and decision-making support. The students will learn to design, develop and validate systems that learn from heterogeneous data (either in a supervised or unsupervised manner) and are able to detect and recognize patterns; 2) they will learn to program the behaviours of autonomous agents (e.g., NAO robots or similar platforms) capable to interact adaptively with humans. The course provides the theoretical foundations of artificial cognitive systems, but it is essentially practical and application-oriented. The students will gather hands-on experience on frameworks and libraries such as PYTORCH for deep learning; on libraries for multimedia signal processing and data mining; on languages supporting the development of semantic web and logic programming applications.

The course involves frontal lessons, laboratories, and seminars. Attendance is strongly recommended. Attending and actively participating in the classroom activities will contribute positively towards the overall assessment of the oral exam.

Should teaching be carried out in mixed mode or remotely, it might be necessary to introduce changes with respect to previous statements, in line with the programme planned and outlined in the syllabus.

Part 1: Knowledge Representation, Reasoning, and Semantic Technologies

• Introduction to Knowledge-Based Systems and to Knowledge Representation
• Rational agents and their environments: from reactive agents to autonomous agents. The general SOAR cognitive architecture.
• Reasoning: deductive and inductive reasoning; reasoning with uncertainty; case-based reasoning. Bayes networks and probabilistic inference
• Problem solving: search strategies and optimization
• The Logic approach: First order logic and logic programming. Fuzzy logic and the computing with words approach. Strengths and limitations.
• The Semantic Web: The RDF Data Model. OWL: The Web Ontology Language. Ontology Engineering. Examples in Protege. The SPARQL query language. Reasoners. Other Semantic Web Technologies and Applications. Linked data.

Part 2: Machine learning and knowledge discovery from large scale multimedia data

• Supervised learning: Regression, Support Vector Machines, Decision trees, KNN
• Neural models: networks, model design, backpropagation, Gradient descent. Model capacity, overfitting and underfitting, regularization.
• Deep Learning: tensors, deep learning frameworks, data augmentation, training strategies.
• Deep learning Architectures: Convolutional Neural Networks (CNN) ; Recurrent Neural Networks (RNN); Autoencoders; GAN and CGAN
• Problem solving through natural computation: reinforcement learning and evolutionary algorithms.
• Multimedia analysis: Fundamental of multimedia signal processing (audio, video, biosignals). Image representations. Artificial vision. Object detection and recognition. Semantic segmentation. Text representations.
• Knowledge discovery from data: the general data mining process, model construction and testing, performance evaluation and metrics, validation, cross-validation, visualization, model explainability.
• Applications

Part 3: Autonomous agents and the NAO humanoid robotic platform

• Theories of perception, action and interaction. Interactive autonomous agents. Human-robot interaction
• The Nao robot operating system (NAOqi), the graphical programming environment Choreographe, NAO SDK.
• Applications. Augmenting the NAO perceptual and cognitive system.

Selected chapters from the following:

1. Artificial Cognitive Systems: A Primer. David Vernon, MIT Press, 2014
2. Artificial intelligence: a modern approach. Stuart Russell, Peter Norvig, 3rd edition, 2010
3. Data Mining: The Textbook, Charu Aggarwal, 2015. Springer
4. Deep Learning. I. Goodfellow, Y. Bengio and A. Courville, MIT Press, 2016
5. A semantic Web Primer (third edition). Grigoris Antoniou, Paul Groth, Frank van Harmelen, and Rinke Hoekstra, 2012. The MIT Press, Cambrigde, Massachusetts, London, England.
6. Teaching materials provided by the instructor