INTELLIGENT SYSTEMS
- Overview
- Assessment methods
- Learning objectives
- Contents
- Bibliography
- Delivery method
- Teaching methods
- Contacts/Info
The course assumes that students have a background acquired on a Bachelor's Degree in Computer Science. Specifically, Students will be expected to be familiar with Vector and Matrix Calculation and Statistics.
The evaluation procedure is based on two methods as follows: - 1)written examination lasting 2 hours. The test consists of 5 questions in general, some entirely of theory, some including numerical exercises. (After correction, the student is invited for a review of the written test; if case the final mark is augmented).
2) Report regarding a topic covered in the course with additional material chosen with the supervision of the teacher
The separate assessment elements contribute towards the final mark according to the following rule:
• Written text 70%
• Project 30%
Course Objectives and Expected Outcomes
The course provides a broad coverage of intelligent systems solving pattern recognition problems. Theoretical concepts in intelligent systems and techniques relevant in real-life applications will be examined. At the end of the course, students will have the ability to appropriately choose the proper technique to solve problems of recognition and /or automatic classification of multidimensional data in several domains.
Upon completion of this course, the students will be able to:
• Examine the prerequisites of a classification method
• Apply feature extraction and selection techniques
• Use statistical techniques with expertise in the limits and strengths of each approach
• Investigate the representative power of supervised neural models, apply heuristics in the choice of network topology, check the condition of overfitting, evaluate performances in training and test.
• Compute Flat Clustering, develop sensitivity analysis and parameter setting
• Investigate the potentialities of Competitive and Self-Organizing approaches
• Design a Fuzzy Set-based System, generate IF-Then Rules
• Evaluate performances of an Intelligent System
• Describe main characteristics of Intelligent Systems for Image Classification, Text Categorization, Multidimensional Biomedical Data Analysis
It is also expected that communication skill and autonomous assessments will be developed through open discussions on topic covered
The acquisition of knowledge and expected skill is developed along the entire course that includes the topics listed below.
1)Introduction to Artificial Intelligence and Pattern Recognition: Historical Perspective, State of the Art of methods and applications -4h
2)Decision-theoretical approaches; supervised classification; learning by example: principles; multidimensional patterns -4 h
3)Feature extraction and selection: Principal Component Analysis,, Pearson correlation coefficient, Information Gain, Sequential Forward Selection, Multidimensional Patterns in Text Classification, Image Recognition and in Content-Based Retrieval- 8h
4) Minimum distance classifier, Bayes’s rule, Maximum likelihood classifier, K-Nearest Neighborhood classifier- 10h
5)Neural Networks: Introduction, Recurrent Neural Networks: Bidirectional Associative networks, Hopfield Networks-3 h
6)Feed forward Models:, Perceptron, Fixed increment rule, Delta rule, Limits of the perceptron model: XOR problem
Multilayer Perceptron, topology, back-propagation learning rule, Applications- 10 h
7)Clustering: principles, K-means,Agglomerative Hierarchical Clustering: Single linkage, Complete linkage- 5
8)Competitive Neural Learning
Self Organizing Maps; Kohonen Networks- 7
9)Soft Computing: Fuzzy Sets Theory, Approximate Reasoning, Neuro-Fuzzy approaches, Fuzzy C-means algorithm -6 h
.
10)DeeepLearning techniques- 5 h
11)Evaluation metrics, evaluation indexes: Kappa index, Jaccard, Dice coefficients; Applications of evaluation metrics in several domains-5 h
12)Design of Intelligent Systems; Demo.- 5 h
Textbook: R.O. Duda, P.E. Hart, and D.G. Stork, Pattern Classification, New York: John Wiley & Sons, 2001
Additional readings, including lecture notes, slides, selected papers from the literature and link s to on line demo will be posted periodically on the class website.
Lectures (72 hours)
Office hours
Office hours is agreed by e-mail.