Computational Intelligence

Credits
5
Types
Compulsory
Requirements
This subject has not requirements , but it has got previous capacities
Department
CS
The objective of this course is to provide the theoretical and practical knowledge necessary for students to be able to efficiently design and implement intelligent systems within the field of Computational Intelligence. Specifically, students will acquire the basic concepts of neural computing, evolutionary computing and fuzzy computing.

Teachers

Person in charge

Others

Weekly hours

Theory
2.4
Problems
0
Laboratory
0.6
Guided learning
0
Autonomous learning
5.925

Competences

Generic Technical Competences

Generic

  • CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to Artificial Intelligence.

    • Technical Competences of each Specialization

    Academic

  • CEA4 - Capability to understand the basic operation principles of Computational Intelligence main techniques, and to know how to use in the environment of an intelligent system or service.
  • CEA8 - Capability to research in new techniques, methodologies, architectures, services or systems in the area of ??Artificial Intelligence.

    • Professional

  • CEP2 - Capability to solve the decision making problems from different organizations, integrating intelligent tools.
  • CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.

    • Transversal Competences

    Information literacy

  • CT4 - Capacity for managing the acquisition, the structuring, analysis and visualization of data and information in the field of specialisation, and for critically assessing the results of this management.

    • Appropiate attitude towards work

  • CT5 - Capability to be motivated for professional development, to meet new challenges and for continuous improvement. Capability to work in situations with lack of information.

    • Objectives

    1. Know the scope of C​omputational Intelligence (CI), and the types of tasks that can be tackled with CI methods
      Related competences: CEA4, CG3,
    2. Know the most important modern computational intelligence techniques
      Related competences: CEA4, CEA8, CG3, CEP2,
    3. Organize the problem solving flow for a computational intelligence problem, analyzing the possible options and choosing the most appropriate techniques or combinations of techniques
      Related competences: CEA8, CG3, CEP2, CEP3, CT4, CT5,
    4. Decide, defend and criticize a solution to a computational intelligence problem, arguing on the strengths and weaknesses of the chosen approach
      Related competences: CEA4, CEA8, CG3, CEP2, CEP3, CT4, CT5,
    5. Learn the fundamentals of neural computation and apply them effectively to develop correct and efficient solutions to a computational intelligence task
      Related competences: CEA4, CEP2, CEP3, CT5,
    6. Learn the fundamentals of evolutionary computation and apply them correctly to develop correct and efficient solutions to computational intelligence tasks.
      Related competences: CEA4, CEP2, CEP3, CT5,
    7. Learn the fundamentals of fuzzy computation and apply them correctly to develop correct and efficient solutions to computational intelligence tasks
      Related competences: CEA4, CEP2, CEP3, CT5,

    Contents

    1. Introduction to Computational Intelligence
      Computational Intelligence: definition and paradigms. Brief historical sketch.
    2. Foundations of Neural Computation
      Introduction to neural computation: biological inspiration, neural network models, architectures and training algorithms, focusinng on Multi-layer Perceptrons and Convolutional Neural Networks. Learning and generalization. Experimantal issues.
    3. Foundations of Evolutionary Computation
      Introduction to evolutionary computation: evolutionary processes in nature, genetic operators, evolutionary optimization algorithms. Genetic algorithms. Evolution Strategies and CMA-ES. Applications and case studies on real problems in regression, classification, identification and system optimization.
    4. Foundations of Fuzzy Computation
      Introduction to fuzzy computation: fuzzy sets and systems, fuzzy inference systems and hybrid. Applications and case studies on real problems in regression, classification, identification and system optimization.

    Activities

    Activity Evaluation act


    Development of topic 1 of the course

    The teacher presents an overview and basic concepts of computational intelligence as well as modern application examples.
    Objectives: 1 2
    Contents:
    Theory
    3h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Development of topic 1 of the course

    The teacher presents the fundamentals of neural computing: inspiration in biological neuron models, architectures and training algorithms. The teacher explains the concepts of learning and generalization and introduces methodologies for obtaining effective models and to guarantee an honest assessment of their effectiveness.
    Objectives: 2 5
    Contents:
    Theory
    12h
    Problems
    0h
    Laboratory
    3h
    Guided learning
    0h
    Autonomous learning
    12h

    Development of topic 3 of the course

    The professor explains the fundamentals of evolutionary computation: evolutionary processes in nature, genetic operators, evolutionary optimization algorithms. Focuses on genetic algorithms and Evolution Strategies and CMA-ES. Points to other existing evolutionary algorithms.
    Objectives: 2 6
    Contents:
    Theory
    9h
    Problems
    0h
    Laboratory
    3h
    Guided learning
    0h
    Autonomous learning
    12h

    Development of topic 4 of the course

    The teacher explains the fundamentals of fuzzy computing: fuzzy sets and fuzzy systems, fuzzy inference systems and FIR.
    Objectives: 2 7
    Contents:
    Theory
    6h
    Problems
    0h
    Laboratory
    3h
    Guided learning
    0h
    Autonomous learning
    12h

    Execution and delivery of 3 practical works


    Objectives: 1 2 3 4 5 6 7
    Week: 15 (Outside class hours)
    Theory
    0h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Exam

    It is a written test on the knowledge of the fundamental concepts of the course

    Week: 14
    Theory
    0h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Teaching methodology

    The topics exposed in the lectures are very well motivated (why is this important?) and motivating (why is this relevant nowadays?) and supplemented with many real examples. These lectures will introduce all the knowledge, techniques, concepts and results necessary to achieve a solid understanding of the fundamental concepts and techniques.

    There are 3 laboratory sessions of 3 hours each spread over the course, to reinforce the theoretical knowledge and as preparation for the three medium-sized practical assignments to be carried out at the end of each of the three major topics covered in the course. There is also a written test of essential knowledge of the subject.

    Evaluation methodology

    The course is scored as follows:

    Three projects will be carried out, one for each of the topics covered in the course, i.e. neural computation, evolutionary computation and fuzzy computation. All the projects will have the same weight and a total mark will be obtained for the projects, which will correspond to 50% of the mark for the course. The other 50% will correspond to the exam mark.

    FINAL GRADE = 50% Projects Grade + 50% Exam Grade

    Bibliography

    Basic

    Complementary

    Web links

    Previous capacities

    Elementary notions of probability, statistics, linear algebra and real analysis