Computer Vision Course
Return to blog

Computer Vision Course

14. February 2024 Print this page 2 Minutes reading time (330 words)

This course will be a hands-on project-based class. The lecture time will be focused on lectures and recurring project presentations. Class projects are to be conducted individually (for example 12 people or groups of 2 Individuals each). Students/groups will be provided credits to complete their project. 


Course Description 

This course is an introduction to the basics of neural networks and computer vision with a focus on image classification and object detection using the no-coding platform Topics include walkthrough convolutional neural networks for computer vision: architectures, training, hyper-parameters, and applications.  


Course Goals 

Upon successful completion of this course, students will be able to: 

  1. Explain the fundamentals of Artificial Intelligence, Machine Learning and Neural Networks 
  2. Work with images and datasets on computer vision 
  3. Understand the concept of training CNN’s as well as create a classification and detection model with use of the platform 
  4. Read and understand state-of-the-art works of literature on deep learning. 


Students will be assigned a topic for reading, research state-of-the-art papers on the assigned topic, and produce a report. 

1. Training a network 1 – classification problem

2. Training a network 2 – detection problem

3. Frameworks and CNN architecture eg. DenseNET, ResNET, mobileNet, VGG

4. Hardware and Software

5. Dataset preparation tips


Each student will have to present their idea of the project.

Run a chosen state-of-the-art scenario available from and report the results in the form of a written report and presentation. Compare different approaches to the problem: manipulating data and fine-tuning the hyperparameters of training.

Chosen and presented in previous milestone projects shall be completed and final reports and presentations are expected.

As an alternative: download a specific model trained and converted in and deploy it in your own application which will process the results and make decisions based on them.


About the Author

Marta Zarzecka
Marta Zarzecka