Under the Hood
Sibylle explains the changes made to the code, including the removal of the soft max layer and the implementation of a confidence measure based on learn centroids. She also discusses the challenges of defining a loss function that makes sense for clustering in deep learning.In this clip
From this podcast
Data Skeptic
Matrix Factorization For k-Means
Related Questions
What is the role of loss functions in machine learning as discussed in the episode 819: PyTorch: From Zero to Hero — with Luka Anicin and the clip Neural Network Dynamics?
What is the role of loss functions in machine learning as discussed in the episode 819: PyTorch: From Zero to Hero — with Luka Anicin and the clip Deep Learning Dynamics?