Delete search term


Quick navigation

Main navigation

Introduction to Neural Networks

Delve into the world of neural networks! From fundamental concepts to practical implementation using Keras and Tensorflow, acquire hands-on skills in designing and evaluating neural networks. Explore diverse applications, including image recognition, through engaging lectures, practical exercises, and a final project presentation.


Compare favorites

At a glance


Certificate of attendance "Introduction to Neural Networks" (2 ECTS)


05.09.2024 17:00, 23.01.2025 17:00


5 evenings


CHF 1'150.00


Language of instruction:


Course dates: 

05.09.2024, 17:00 - 20:00

12.09.2024, 17:00 - 20:00

19.09.2024, 17:00 - 20:00

26.09.2024, 17:00 - 20:00

03.10.2024, 17:00 - 20:00


23.01.2025, 17:00 - 20:00

30.01.2025, 17:00 - 20:00

06.02.2025, 17:00 - 20:00

27.02.2025, 17:00 - 20:00

06.03.2025, 17:00 - 20:00

Objectives and content

Target audience

This course is targeted towards students and professionals who have a basic understanding of machine learning and want to delve deeper into the field of neural networks. It is suitable for individuals with a background in computer science, data science, engineering, or related disciplines.

This course is for anyone interested in neural networks. All enthusiasts who have a keen interest in neural networks and want to understand their principles, applications, and implementation details can also benefit from this course.


After completing the module, students will be able to:

  • understand the neural networks and deep learning theory
  • design, train, and evaluate neural networks for various tasks
  • apply their knowledge to solve problems in various domains, such as image recognition
  • use and implement neural networks and deep learning models in Python using popular libraries and frameworks (Keras/Tensorflow)


Key topics covered in the course include:

  • Neural network basics: Introduction to artificial neurons, activation functions, and network structures
  • Feedforward neural networks: Understanding the structure, forward propagation, and backpropagation algorithm
  • Convolutional neural networks: Understanding the architecture, convolutional layers, pooling, and applications in image and video analysis
  • Deep learning: Introduction to deep neural networks, layer types (convolutional, recurrent, fully connected), and deep learning frameworks
  • Training and optimization: Techniques for training neural networks, gradient descent, regularization, and optimization algorithms
  • Applications of neural networks: Overview of real-world applications, such as image recognition, natural language processing, and speech recognition
  • Practical implementation: Hands-on experience with implementing neural networks using popular deep learning libraries and frameworks

CAS in Digital Life Sciences

This module is part of the CAS in Digital Life Sciences continuing education programme, but can also be attended independently of the CAS. Credit points earned for this module can be credited to the CAS course at a later date, provided the relevant general conditions are fulfilled.

More information here: CAS in Digital Life Sciences

Overview continuing education

You can find an overview of our continuing education programmes in the field of computational science and artificial intelligence here.


The module will consist of lectures and practical exercises. In addition to lectures, students will be required to self-study selected topics. Students will work independently and/or in groups on practical programming exercises, data challenges and present results of their final project at the end of the course.

  • Exercises during the course: 30%
  • Final Project 70%


There are 5 lessons organized once a week on Thursday Afternoon. After 4 lessons the students work on their final project for about two weeks. The final project presentation will be held during the last lesson.

Enquiries and contact

  • Dr. Martin Rerabek

    Dr. Martin Rerabek is a senior researcher and lecturer at the Institute of Computational Sciences (ICLS) at ZHAW. His multi-disciplinary educational background background lies in electronic engineering, signal, image and video processing, and machine learning. At ZHAW, he focuses on development of applications tackling real-world challenges in machine learning, pattern recognition and predictive maintenance.



Admission requirements

Ideally, the course requires prior knowledge as provided by the courses:

- Einführung ins Programmieren mit Python

- Data Analysis Fundamentals

- Machine Learning Fundamentals in Python

Start Application deadline Registration link
05.09.2024 17:00 22.08.2024 Application
23.01.2025 17:00 09.01.2025 Application