Machine Learning with Neural Networks Field of study: Biophysics
Programme code: W4-S2BFA21.2022

Module name: Machine Learning with Neural Networks
Module code: W4-2BF-MB-21-17
Programme code: W4-S2BFA21.2022
Semester:
  • summer semester 2025/2026
  • summer semester 2024/2025
  • summer semester 2023/2024
  • summer semester 2022/2023
Language of instruction: English
Form of verification: course work
ECTS credits: 4
Description:
Course syllabus: (1) Introduction to Machine Learning (fundamental problem and its inherent complexity; general approaches for its solution) (2) Classic Neural Networks models (Hopfield model; recurrent Boltzmann Machines (BM) and Restricted Boltzmann Machines (RBM); learning with BM y RBM: gradient descent, Contrastive Divergence and its variants; single-layer perceptrons (SLP): lineal and logistic regression, Rosenblat perceptron; multi-layer perceptrons (MLP): learning with MLP, back-propagation; Convolutional Neural Networks (CNN): model, link to MLP, and learning) (3) Deep Learning: link with classical models and modern learning techniques.
Prerequisites:
(no information given)
Key reading:
(no information given)
Learning outcome of the module Codes of the learning outcomes of the programme to which the learning outcome of the module is related [level of competence: scale 1-5]
students will be able to state the fundamental problem and complexity of Machine Learning, and acquire a global view of the different Machine Learning techniques [MB_17_1]
 KBF_W02 [4/5] KBF_U02 [3/5] KBF_U11 [4/5] KBF_U14 [5/5] KBF_K10 [3/5]
students will be able to understand and explain classical models of Neural Networks such as the Hopfield networks, Boltzmann Machines, Single- and Multi-layer Perceptrons, and Convolutional networks [MB_17_2]
 KBF_W02 [4/5] KBF_U02 [3/5] KBF_U11 [4/5] KBF_U14 [5/5] KBF_K10 [3/5]
students will be able to implement the standard training techniques in these models, and put them in relation with the issue of the Deep Learning and its solution techniques [MB_17_3]
 KBF_W02 [4/5] KBF_U02 [3/5] KBF_U11 [4/5] KBF_U14 [5/5] KBF_K10 [3/5]
Type Description Codes of the learning outcomes of the module to which assessment is related
credit [MB_17_w_1]
The final mark for this course is computed as 0.2*M_1 + 0.2*M_2 + 0.6*M_3, where M_n is the grade of each practical homework. For the latter, the students will be provided with a code structure, and they will have to implement specific functions and run virtual experiments in which different machine learning strategies will be employed
 MB_17_1 MB_17_2 MB_17_3
Form of teaching Student's own work Assessment of the learning outcomes
Type Description (including teaching methods) Number of hours Description Number of hours
lecture [MB_17_fs_1]
Detailed discussion by the lecturer of the issues listed in the table "module description" using the table and/or multimedia presentations
 26
Supplementary reading, working with the textbook
 44 credit [MB_17_w_1]
laboratory classes [MB_17_fs_2]
Computer sessions
 10
(no information given)
 20 credit [MB_17_w_1]
Attachments
Module description (PDF)
Information concerning module syllabuses might be changed during studies.
Syllabuses (USOSweb)
Semester Module Language of instruction
(no information given)