Checking date: 03/05/2019


Course: 2019/2020

Automatic Programming
(16444)
Study: Master in Computer Science and Technology (71)
EPI


Coordinating teacher: ALER MUR, RICARDO

Department assigned to the subject: Department of Computer Science and Engineering

Type: Electives
ECTS Credits: 3.0 ECTS

Course:
Semester:




Students are expected to have completed
Although it is not necessary, it is useful to have taken subjects related to machine learning (data mining, neural networks, evolutionary computation, ...).
Competences and skills that will be acquired and learning results.
- To know the different types, techniques, and domains, of Automatic Programming (AP) - To know how how AP techniques have been applied to some real domains - To be able to do research work in PA - To know the scientific method and being able to perform rigorous evaluation of results - To be able to use AP and advanced machine learning tools - To be able to understand and critically asses PA research articles - To know the different types of publications in PA (surveys, empirical comparisons, original contributions, ...) - To be able to present scientific contributions - To be able to know if PA techniques can be applied to specific problems
Description of contents: programme
1. Introduction 2. Deep Learning: 2.1. Deep Neural Networks 2.2. Recurrent Neural Networks 2.3. Advanced topics in Deep learning 3. Evolutionary-computation 3.1. Genetic Programming 3.2. Estimation of distribution algorithms (Probabilistic Incremental Program Evolution/PIPE) 4. Inductive Logic Programming/ILP 4.1. Basic ILP techniques 4.2. Relational Data Mining 5. Advanced reinforcement-learning 5.1. Dynamic programming 5.2. model-free and model-based methods 5.3. Generalization in reinforcement-learning 5.4. Knowledge-transfer in reinforcement-learning
Learning activities and methodology
- Lectures - Tutorials - Student's individual work
Assessment System
  • % end-of-term-examination 0
  • % of continuous assessment (assigments, laboratory, practicals...) 100
Basic Bibliography
  • Dzeroski S. and Lavrac. Relational Data Mining.. Springer-Verlag. 2001
  • Ian Goodfellow, Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press (http://www.deeplearningbook.org). 2016
  • Koza, John R. Genetic programming : on the programming of computers by natural selection.. MIT PRESS.
  • Lavrac, N. and Dzeroski, S. Inductive Logic Programming: Techniques and Applications. Ellis Horwood, New York. 1994
  • Mitchell, T.M.. Machine Learning. McGraw Hill. 1997
  • R. Sutton y A. Barto.. Reinforcement Learning: an Introduction. The MIT Press. 1998
Recursos electrónicosElectronic Resources *
Additional Bibliography
  • Koza, John R.. Genetic Programming II: Automatic Discovery of Reusable Programs. MIT PRESS.
  • O-Reilly, Una-May et al. (eds.). Evolutionary Computation. Trends in Evolutionary Methods for Program Induction. MIT PRESS.
  • Olsson, J. R.. Inductive functional programming using incremental program transformation. Artificial Intelligence. Vol. 74:1, 55-83. Elsevier. 1995
(*) Access to some electronic resources may be restricted to members of the university community and require validation through Campus Global. If you try to connect from outside of the University you will need to set up a VPN


The course syllabus and the academic weekly planning may change due academic events or other reasons.