Search

Low Resource Neural Networks for Health Monitoring


Description While deep learning systems are revolutionising what is possible in deep learning they require a large amount of computational resources such as memory and power to run effectively. This limits their application in real-world embedded and smart devices 
Task The interested student(s) will explore low resource deep learning topologies such as spiking and binary networks on a range of health-related classification tasks 
Utilises Python and related deep learning toolkits
Requirements Preliminary knowledge in Machine Learning, Good programming skills (e.g. Python, C++)
Languages English
Supervisor Dr. Nicholas Cummins (nicholas.cummins@informatik.uni-augsburg.de)