PhD position on statistical theory for deep learning based image classification

at  Universiteit Twente

KEY TAKEAWAYS

• 
  Hours
  40 hr.
• 
  Salary indication
  Salary gross/monthly
  based on full-time
  € 2,872 - € 3,670
• 
  Deadline
  6 Sep 2024
  From recognising faces to diagnosing diseases, convolutional neural networks (CNNs) excel in image recognition. However, their lack of theoretical understanding poses the risk of unexpected behaviour. How do CNNs detect and classify objects? To address this, we must first step back and ask: What is the appropriate model for analysing image classification? What are the properties of CNNs? How do they learn?
  This PhD project seeks to shed light on these questions by applying statistical theory. You will investigate the theoretical properties of various network architectures, assess how network depth influences performance and delve into the learning processes of CNNs. Applications to medical image data will connect the derived theory with practical applications.
  The UT and the faculty EEMCS are inclusive toward underrepresented groups and strive to increase the proportion of female staff. Female applicants are particularly welcome.

Please refer the Job description for details