Darryl and I discuss his background, how he became interested in machine learning, and a project we are currently working on investigating the penalization of polysemanticity during the training of neural networks.

Diagram detailing information flow for the research on penalizing polysemanticity discussed in this episode


01:46 - Interview begins
02:14 - Supernovae classification
08:58 - Penalizing polysemanticity
20:58 - Our “toy model”
30:06 - Task description
32:47 - Addressing hurdles
39:20 - Lessons learned

Links to all articles/papers which are mentioned throughout the episode can be found below, in order of their appearance.