Updates

• experiments with caltech 101
  • too small dataset. Network needs pretraining
  • too big bictures. problems with gpu memory when training and big storage space when saving models
• refactor code to better scale for more evaluation techniques
• reviewed XAI methods.
• Further literature review for representation learning

MS Student Updates

• Melanie
  • Image Segmentation on Steel Defect dataset
  • Next on: Deep Optical Flow

Other activities

• Hololens 2 review
• plan to publish the AR project as internship position
  • LinkedIn -> CPS page?
  • MUL
  • Emails
• Share Christmas video with the public relations team of MUL
• linked in account ->  page

Next on

• do experiments for interpolating latent space
• run experiments with more datasets
• reconstruct the paper for
  • ICML
  • IJCAI
• literature review on representation learning
• seminar talk for latent space representation and explainability in neural networks, feature maps. organize meetings (1 paper per week)