Sign up to save your podcasts
Or
Share Novel Loss Functions for Improved Data Visualization in t-SNE
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Novel Loss Functions for Improved Data Visualization in t-SNE
Today's article comes from the journal of Machine Learning and Knowledge Extraction. The authors are Nassar et al., from Hamad Bin Khalifa University, in Qatar. In this paper they're evaluating two replacements for KL-divergence within t-SNE. Max-Flipped KL Divergence (KLmax) and KL-Wasserstein Loss.
View all episodes
By JournalClub.ioToday's article comes from the journal of Machine Learning and Knowledge Extraction. The authors are Nassar et al., from Hamad Bin Khalifa University, in Qatar. In this paper they're evaluating two replacements for KL-divergence within t-SNE. Max-Flipped KL Divergence (KLmax) and KL-Wasserstein Loss.