Navigation

19D051NM - Neural Networks

Course specification
Course title Neural Networks
Acronym 19D051NM
Study programme Electrical Engineering and Computing
Module System Control and Signal Processing
Type of study doctoral studies
Lecturer (for classes)
Lecturer/Associate (for practice)
    Lecturer/Associate (for OTC)
      ESPB 9.0 Status elective
      Condition none
      The goal Introducing students to the basic concepts of neural networks, different architectures, and the learning capabilities of neural networks, etc. Training students to independently design systems based on neural networks for engineering applications, digital signal processing, control, pattern recognition, quality control, and related fields...
      The outcome students will be able to independently analyze and synthesize various types of neural networks applied in many fields of engineering. They will also learn to apply different learning and training algorithms for neural networks and to implement them using the MATLAB software package or in Python.
      Contents
      Contents of lectures An overview of the history of neural networks and architectures; training, generalization, and initialization of neural networks. Convergence properties of algorithms. Nonlinear modeling of dynamic black-box systems. Classification and clustering using neural networks. Convolutional neural networks. Deep neural networks. LSTM networks and transformers
      Contents of exercises Practical instruction will be conducted through the design of neural networks using concrete examples, including training and validation.
      Literature
      1. Grokking Deep Learning, Andrew Trask, Manning, 2019 (Original title)
      2. M. Nielson, Neural Networks and Deep Learning, Determination press, 2015 (Original title)
      3. Neural Networks for Pattern Recognition, Christopher Bishop, Oxford University Press, 2000. (Original title)
      4. Handbook of Neural Network Signal Processing, Ed. by Yu Hen Hu and Jenq-Neng Hwang, CRC Press, 2002. (Original title)
      5. C. Bishop, Neural networks and pattern recognition, Prentice Hall, 2000 (Original title)
      Number of hours per week during the semester/trimester/year
      Lectures Exercises OTC Study and Research Other classes
      8
      Methods of teaching lectures and auditory exercises
      Knowledge score (maximum points 100)
      Pre obligations Points Final exam Points
      Activites during lectures 0 Test paper 70
      Practical lessons 0 Oral examination 0
      Projects 0
      Colloquia 30
      Seminars 0