n.BA.AD.NeuNe.23HS (Neural Networks) 
Module: Neural Networks
This information was generated on: 10 May 2024
No.
n.BA.AD.NeuNe.23HS
Title
Neural Networks
Credits
4

Description

Version: 1.0 start 01 August 2023

 

Study Programme Applied Digital Life Sciences
Regulations Applicable RPO, 29 January 2008, School of Life Sciences and Facility Management Academic Regulations, 15 Dec. 2009, Annex for the Bachelor of Applied Digital Life Sciences degree programme
Module Type  
X Compulsory Module    Elective Module    Optional Module
Planned Semester 4th Semester
Module Coordinator Martin Schüle
Telephone / E-Mail +41 (0)58 934 57 84 / martin.schuele@zhaw.ch
Lecturer(s),
Speaker(s),
Associate(s)		 Martin Schüle
Entrance Requirements Maschinelles Lernen
Learning Outcomes and Competencies Technical skills:
Students will acquire a working knowledge of current neural network (NN) and deep learning (DL) techniques and apply them to problems in the field of life sciences.
After completing the module, students will be able to:
  • judge on the advantages and disadvantages of different NN and DL architectures and corresponding applications
  • adapt and apply suitable NN and DL techniques to problems in life sciences
  • learn about new methods in the field on their own.
 
Transferable skills:
The students will be able to reflect the usage of DL and AI in a life sciences context and regarding technical, economic and social challenges.
Module Content The module covers the following topics:
  • Biological basis of neural networks (NN)
  • Basic mathematical concepts of NN
  • Basics of NN: Perceptron, Multilayer Perceptron
  • Basics of DL: Training of DL models, optimizers, regularization
  • Introduction to Python and Tensorflow for DL applications
  • Simple DL models: CNN, RNN, LSTM
  • Case studies in life sciences
Follow-up Modules -
Methods of Instruction  Lectures, guided exercises, group work
Digital Resources
  • Learning videos
  • Exercises and application tasks (incl. solutions)
  • Case studies
Lesson Structure / Workload  
 Contact Hours 28
 Guided Self-Study 28
 Independent Self-Study 64
 Total Workload 120
Classroom Attendance Attendance is strongly encouraged but not enforced with attendance list
Assessment
  • Project work during the semester 30%
  • Written exam at the end of the semester 70%
 
If there is a low number of participants, the lecturer may change the form of a repeat examination after consultation with the head of the study programme: e.g. an oral examination can be used to replace a written one. Please report any changes to the form of examinations by e-mail to pruefungsadmin.lsfm@zhaw.ch and Cc. Head of study programme.
Language of Instruction  English
Comments -

 

Course: Neural Networks
No.
n.BA.AD.NeuNe.23HS.V
Title
Neural Networks

Note

  • No module description is available in the system for the cut-off date of 10 May 2024.