This information sheet indicates how the course will be organized at pandemic code level yellow and green.
If the colour codes change during the academic year to orange or red, modifications are possible, for example to the teaching and evaluation methods.

Artificial Neural Networks

Course Code :2500WETANN
Study domain:Computer Science
Academic year:2020-2021
Semester:2nd semester
Contact hours:45
Study load (hours):168
Contract restrictions: No contract restriction
Language of instruction:English
Exam period:exam in the 2nd semester
Lecturer(s)José Antonio Oramas Mogrovejo

3. Course contents *

The content of the course is divided into two parts. In the first part of the course basic concepts related to artificial neural networks will be introduced. Shallow feed-forward and recurrent architectures will be the core of this part. Associated applications related to images, text and speech analysis will complement these topics. The first part of the course concludes with a walk-through through standard procedures to train shallow neural networks.

From the foundations set by the first part, the second part of the course will focus on automatic learning with deeper architectures, a.k.a. "Deep Learning". This part of the course will cover deep counterparts of the shallow architectures studied in the first part plus more recent types of layers that have been proposed.

Some of the topics to be convered include:

  • Multi-layer Perceptron
  • Convolutional Neural Networks
  • Residual Learning
  • Sequential prediction with Neural Networks
  • Deep generative neural networks
  • Interpretation and Explanation of Deep Neural Networks.
  • Revision of recent nominal papers