The course aims to present the foundation models, methods and techniques in the areas of Artificial Intelligence, such as problem-solving, search in complex environments, adversarial search, knowledge representation and constraint management. Some toy domains useful for understanding the practical application of the concepts covered in the course will be studied.
Lectures and exercises conducted during the course will allow the student to acquire basic analytical and problem-solving skills on various domains of interest to the discipline.
Lectures and exercises conducted during the course will allow the student to acquire basic analytical and problem-solving skills on various domains of interest to the discipline.
Curriculum
teacher profile teaching materials
Camera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Programme
Elements of Perspective ProjectionCamera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Type of evaluation
Open-ended questions. teacher profile teaching materials
- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Programme
1. Introduction to the Course- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Core Documentation
Lecture slides.Attendance
Attendance is not compulsory, but it is strongly recommended.Type of evaluation
Written exam. teacher profile teaching materials
Camera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Mutuazione: 20810515 FONDAMENTI DI INTELLIGENZA ARTIFICIALE in Ingegneria Informatica e dell'Intelligenza Artificiale L-8 R RUSSO PAOLO, SANSONETTI GIUSEPPE
Programme
Elements of Perspective ProjectionCamera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Type of evaluation
Open-ended questions. teacher profile teaching materials
- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Mutuazione: 20810515 FONDAMENTI DI INTELLIGENZA ARTIFICIALE in Ingegneria Informatica e dell'Intelligenza Artificiale L-8 R RUSSO PAOLO, SANSONETTI GIUSEPPE
Programme
1. Introduction to the Course- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Core Documentation
Lecture slides.Attendance
Attendance is not compulsory, but it is strongly recommended.Type of evaluation
Written exam. teacher profile teaching materials
Camera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Mutuazione: 20810515 FONDAMENTI DI INTELLIGENZA ARTIFICIALE in Ingegneria Informatica e dell'Intelligenza Artificiale L-8 R RUSSO PAOLO, SANSONETTI GIUSEPPE
Programme
Elements of Perspective ProjectionCamera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Type of evaluation
Open-ended questions. teacher profile teaching materials
- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Mutuazione: 20810515 FONDAMENTI DI INTELLIGENZA ARTIFICIALE in Ingegneria Informatica e dell'Intelligenza Artificiale L-8 R RUSSO PAOLO, SANSONETTI GIUSEPPE
Programme
1. Introduction to the Course- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Core Documentation
Lecture slides.Attendance
Attendance is not compulsory, but it is strongly recommended.Type of evaluation
Written exam. teacher profile teaching materials
Camera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Mutuazione: 20810515 FONDAMENTI DI INTELLIGENZA ARTIFICIALE in Ingegneria Informatica e dell'Intelligenza Artificiale L-8 R RUSSO PAOLO, SANSONETTI GIUSEPPE
Programme
Elements of Perspective ProjectionCamera Calibration
Elements of Epipolar Geometry
Elements of 3D Reconstruction
Image Filtering
Elements of Deep Learning Applied to Images
Type of evaluation
Open-ended questions. teacher profile teaching materials
- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Mutuazione: 20810515 FONDAMENTI DI INTELLIGENZA ARTIFICIALE in Ingegneria Informatica e dell'Intelligenza Artificiale L-8 R RUSSO PAOLO, SANSONETTI GIUSEPPE
Programme
1. Introduction to the Course- Areas of Interest in Artificial Intelligence.
- Potential of AI Models and Methods.
2. Problem Solving by State Space Search
- Uninformed Search (Breadth-First, Cost-Driven, Depth-First, Iterative Deepening).
- Heuristic Search (Best First, A* Algorithm, Heuristic Functions).
- Approximate Algorithms (Hill Climbing, Simulated Annealing, etc.).
- Adversarial Search (MiniMax, Alpha-Beta Pruning).
3. Introduction to the Python Language
- Development Environments, Jupyter Notebook, Colab.
- Basic Python. Data Structures in Python.
- Python Libraries: NumPy, Pandas, Matplotlib, ScikitLearn.
4. Evolutionary Computation
- Soft Computing and the “No Free Lunch Theorem”.
- Genetic Algorithms and their Applications.
- Particle Swarm Optimization and Applications.
5. Communication and Perception
- Computer Vision:
• Light and Color
• Image Formation
• Visual Stream Processing
• Object Recognition Techniques
Core Documentation
Lecture slides.Attendance
Attendance is not compulsory, but it is strongly recommended.Type of evaluation
Written exam.