|
Type A
|
Code |
Competences Specific | | | A1 |
Integrate the fundamental technology, applications, services and systems of Computer Security and Artificial Intelligence,in a broader, multidisciplinary context.
|
| | A7 |
Understand and apply advanced knowledge of high performance computing and numerical or computational problems related to artificial intelligence neural networks and evolutionary systems methods.
|
| | G2 |
Perform mathematical modelling, calculation and simulation in company technology and engineering centres, particularly in tasks of research, development and innovation in the areas of Computer Security and Artificial Intelligence
|
|
Type B
|
Code |
Competences Transversal | | | CT3 |
Solve complex problems critically, creatively and innovatively in multidisciplinary contexts. |
|
Type C
|
Code |
Competences Nuclear |
|
Type A
|
Code |
Learning outcomes |
| | A1 |
Analyse the problems and their causes from a global focus in the medium and long term.
| | | A7 |
Understand the difficulty in handling real multidimensional data, and know some classical linear techniques.
Know neuronal and evolutionary computing techniques applicable to problems regarding the prediction, classification, optimisation, grouping and display of multidimensional data.
| | | G2 |
Apply the techniques learned in a specific context.
|
|
Type B
|
Code |
Learning outcomes |
| | CT3 |
Recognise the situation as a problem in a multidisciplinary, research or professional environment, and take an active part in finding a solution.
Follow a systematic method with an overall approach to divide a complex problem into parts and identify the causes by applying scientific and professional knowledge.
Design a new solution by using all the resources necessary and available to cope with the problem.
Draw up a realistic model that specifies all the aspects of the solution proposed.
Assess the model proposed by contrasting it with the real context of application, find shortcomings and suggest improvements.
|
|
Type C
|
Code |
Learning outcomes |
| Topic |
Sub-topic |
| Multidimensional data |
Basic problems: prediction, classification, optimization, clustering, visualization. Data types: discrete, real, cathegorical. Data preprocessing: outliers, missing data, scaling. |
| Neuronal computation |
McCulloch & Pitts model: weightes, threshols, fields, activation function, activation. Artificial neural network architectures. Neuronal models classification. |
| Associative memory and optimization |
Hopfield networks: Hebb rule, dynamics, energy. Application for combinatiorial optimization. |
| Supervised learning |
Linear model: multilinear regression. Simple perceptron. Linear networks. Linear separability. Multilayer networks. Back-propagation. Variants of Back-propagation. Cascade Correlation. Support Vector Machines. Other algorithms. |
| Unsupervised learning |
Linear model: principal component analysis. Self-supervised networks. Hebbian learning. Competitive learning. Self-Organized Maps. Adaptive Resonance Theory. Other algorithms. |
| Evolutionary computation |
Genetic algorithms: chromosome, population, reproduction, recombination, mutation, fitness. Genetic programing. Particle Swarm Optimization. Other algorithms. |
| Methodologies :: Tests |
| |
Competences |
(*) Class hours
|
Hours outside the classroom
|
(**) Total hours |
| Introductory activities |
|
1 |
1.5 |
2.5 |
| Lecture |
|
28 |
43.5 |
71.5 |
| IT-based practicals in computer rooms |
|
10 |
15 |
25 |
| IT-based practicals |
|
4 |
6 |
10 |
| Personal attention |
|
1 |
0 |
1 |
| |
| Oral tests |
|
1 |
1.5 |
2.5 |
| |
(*) On e-learning, hours of virtual attendance of the teacher.
(**) The information in the planning table is for guidance only and does not take into account the heterogeneity of the students. |
Methodologies
| |
Description |
| Introductory activities |
Introduction to the development of the course and its contents |
| Lecture |
Contents exposition and availability of the bibliographic materials |
| IT-based practicals in computer rooms |
Exposition of tools for the development of solutions and practical resolution of problems |
| IT-based practicals |
Practical exercises to attain experience and consolidate the theoretical knowledge |
| Personal attention |
Personal tuition |
|
Description |
|
Solving doubts about contents and practical exercises. In person, by email or videoconference.
|
|
Methodologies |
Competences
|
Description |
Weight |
|
|
|
|
| IT-based practicals |
|
Evaluation of practical exercises |
85% |
| Oral tests |
|
Exposition of a method related with the course |
15% |
| Others |
|
|
|
| |
|
Other comments and second exam session |
|
Second call: practical exercises 100% |
| Basic |
Hertz, J.A., Krogh, A., Palmer, R.G., Introduction to the Theory of Neural Computation, Addison-Wesley, 1991
Ke-Lin Du, M. N. S. Swamy, Neural Networks and Statistical Learning, Springer, 2014
S.N. Sivanandam, S. N. Deepa, Introduction to Genetic Algorithms, Springer, 2008
|
|
| Complementary |
|
|
(*)The teaching guide is the document in which the URV publishes the information about all its courses. It is a public document and cannot be modified. Only in exceptional cases can it be revised by the competent agent or duly revised so that it is in line with current legislation. |
|