Channels
00-announcements
01-intros
02-general-community-chat
03-ai-events
04-coworking
05-ai-news
06-technical-discussion
07-self-promotion
08-random-memes
09-job-board
Powered by
#07-self-promotion
Title
# 07-self-promotion
j
Jugal Patel
10/05/2023, 4:48 PM
What if you could see exactly what your image classifier has learned? What if you could catch bias and confusion before deployment? Introducing Prototype Generation, a data-independent feature visualisation method that maintains natural internal activation paths and produces trustworthy insights.
Leap Labs' brilliant researcher Arush Tagade introduces this concept in our first publication on Arxiv
.
👀 1
Post