Sign Up to like & get
recommendations!
1
Published in 2022 at "Artificial intelligence"
DOI: 10.3390/ai3010013
Abstract: A major bottleneck preventing the extension of deep learning systems to new domains is the prohibitive cost of acquiring sufficient training labels. Alternatives such as weak supervision, active learning, and fine-tuning of pretrained models reduce…
read more here.
Keywords:
active learning;
weak supervision;
supervision;
labeling functions ... See more keywords