This lab module will enable you to develop skills essential for carrying out individual research projects in Deep Learning applied to EEE problems. You will be organized in small groups (4 students) and assigned a project from robotics, computer vision or communications. The Lab will focus on structured programming exercises, data preparation, and evaluation of the developed software model.

Upon successful completion of this module, you will be able to: 1) apply the process of developing a machine learning approach to an EEE problem 2) design and implement an ML approach on hardware with sensors 3) prepare data for typical learning tasks such as classification and regression 4) create a model from a given data 5) evaluate the performance of the developed model 6) critically analyse the results and draw appropriate conclusions

The module is based on practical work with embedded device but designed so that students can support their learning with self-study. The main goal is to build a hardware device with sensors which will collect data for online or offline processing. A machine learning model will then be trained to analyse the data and make predictions/decisions. It is spread over approximately 20 working weeks with 5 milestones. Projects are in groups of 4-5 students that design the system and interact for the entire project duration. Each student within the group builds the same hardware and carries out the same experiments. Each group produces one report and presentation.