COGNITIVE COMPUTING AND ARTIFICIAL
Academic Year 2024/2025 - Teacher: Daniela GIORDANOExpected Learning Outcomes
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, knowledge
representation, natural computation, logic, and automated reasoning to
solve typical and topical problems in application scenarios such as
business intelligence, decision-making support, human-computer
interaction, and human-robot interaction. The course provides the
theoretical foundations of artificial cognitive systems but is practical
and application-oriented. The students will gather hands-on experience
with cutting-edge techniques of neuro-symbolic AI preparing them for
research or industry roles in AI.
Learning objectives:
Knowledge and understanding
- Understand the key tenets of modern cognitive architectures
- Understand the mechanisms underlying classical, neural, and reinforcement learning methods
- Understand differences in approaches to performing reasoning and inference
- Understand the scope of applicability of pre-trained foundation
models, advanced deep learning architectures, and hybrid solutions
Applying knowledge and understanding
- Be able to design, develop, and validate systems that learn from heterogeneous data (text, images, audio, temporal sequences)
- Be able to design, develop, and query a knowledge graph
- Be able to prototype autonomous agents' behaviors capable of interacting adaptively with humans.
Making judgements
- Recognize when a problem is best solved by a machine learning approach or by a symbolic AI approach
- Recognize the limitations, risks, and ethical implications of deploying Artificial Intelligence technologies
Communication skills
- Present orally in English AI methods and architectures to solve domain-specific problems
- Document software choices in commented Python notebooks
- Explain the motivations behind specific design choices
Learning skills
- Learning to read effectively scientific papers written in English to focus on the key idea and recognize the article's contribution
- Learning to repurpose creatively software artifacts
- Learning to collaborate to solve a problem and prepare a joint report
Course Structure
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.
Required Prerequisites
- Proficiency in Python programming
- Basic knowledge of calculus, linear algebra, and probability
- Understanding of basic machine learning concepts
- Familiarity with machine learning libraries (e.g., PyTorch, TensorFlow) is not mandatory but is an asset.
- Attendance in the Deep Learning course in the LM32 curriculum is strongly recommended
Attendance of Lessons
Strongly recommended. Attending and actively participating in classroom activities will contribute positively to the overall
assessment of the oral exam.
Detailed Course Content
Textbook Information
Selected chapters from the following:
- Artificial Cognitive Systems: A Primer. David Vernon, MIT Press, 2014
- Artificial intelligence: a modern approach. Stuart Russell, Peter Norvig, 3rd edition, 2010
- Deep Learning. I. Goodfellow, Y. Bengio and A. Courville, MIT Press, 2016
- Teaching materials provided by the instructor
Course Planning
| Subjects | Text References | |
|---|---|---|
| 1 | IRational agents and their environments: from reactive agents to autonomous agents. The general SOAR cognitive architecture. Developmental cognitive architectures. The concept of embodied cognition. The problem of knowledge representation. | 1, 2 |
| 2 | Reasoning: deductive and inductive reasoning; reasoning with uncertainty; case-based reasoning. Causal inference. Argumentation and explanation. | 2,4 |
| 3 | Problem-solving: search strategies and optimization. Problem-solving by search vs. Problem-solving by description. Semantic nets and similarity metrics | 2,4 |
| 4 | Semantic technologies. Knowledge graphs. Ontologies. Query languages for knowledge graphs | 2,4 |
| 5 | First-order logic and logic programming. Other logics: fuzzy and temporal logic. Strengths and limitations | 4 |
| 6 | Deep neural models: Autoencoders and Variational autoencoders; Generative Adversarial Networks (GANs). Recurrent Neural Networks (RNN). | 3 |
| 7 | The Transformers Architecture and Attention Mechanism. Embedding methods. Pre-trained Large Language Models (LLMs) and the revolution of multimodal foundation models: GPT-3, BERT, CLIP, DALL-E, SORA. Pre-training objectives: masked language modeling, autoregressive modeling. | 3,4 |
| 8 | Prompting and fine-tuning. Pre-processing text, audio/speech, image/video, and biosignals for use with foundational models. Evaluation metrics for foundation models. Applications in Natural Language Processing: Text generation, summarization, translation, and question answering. Applications in Computer Vision: Vision transformers in medical imaging | 3,4 |
| 9 | Learning paradigms: Self-supervised Learning, Meta-learning. Continual Learning. Federated learning. | 4, 6 |
| 10 | Reinforcement learning: Markov Decision Processes (MDP). Dynamic programming. Basic RL Algorithms. Deep reinforcement learning (DRL) concepts. Key algorithms: Deep Q-Networks (DQN), Policy Gradient Methods. Proximal Policy Optimization (PPO). | 4 |
| 11 | The challenge of Language understanding and knowledge integration. Model hallucinations. Chatbot development with LLMs, Retrieval Augmented Generation, Knowledge Graphs, and Reinforcement Learning. Integrating Symbolic and Sub-symbolic AI. | 4 |
| 12 | Explainable AI. Methods for making the models interpretable.Ethical considerations in AI. Addressing bias, fairness, and accountability. Case studies on ethical issues in AI. Bias in AI systems: Identification and mitigation strategies. | 4 |
| 13 | Theories of perception, action and interaction. Interactive autonomous agents. Human-robot interaction. The challenges of multimodal interaction. The Reachy antropomorphic robot | 1,4 |
Learning Assessment
Learning Assessment Procedures
The competencies to be developed by the students will be tested by an
oral exam consisting of the discussion of project work (60% of the final
grade), presentation of a research article (10% of the grade), and 3
questions on key concepts and methodologies covered in the course (30%
of the grade). Assessment criteria of the project work include depth of
analysis, adequacy, correctness, and originality. Assessment criteria
of the oral include the ability to justify and critically evaluate the
technological solutions adopted in the project/homework, and clarity.
Examples of frequently asked questions and / or exercises
Examples of questions and projects are available in Studium