recentpopularlog in

yencarnacion : problem   15

Making AI Work with Small Data | IndustryWeek
# Synthetic data generation
## GANs, variational autoencoders, domain randomization and data augmentation can be used to do this
# Transfer learning
# Self-supervised learning
# few-shot learning
## reformulating problem to help the AI system to learn an easier, less data hungry inspection task while achieving the same goal
One-shot learning
# anomaly detection
## flag anything that deviates significantly from the OK images as a potential problem.
# Hand-coded knowledge
# Human-in-the-loop
## AI shows something to a human expert and defers to their judgement when not sure
big  small  data  ai  artificial  intelligence  machine  learning  challenge  challenges  lack  of  problem  with 
6 weeks ago by yencarnacion

Copy this bookmark:





to read