Seer: SElf-supERvised algorithm from Facebook
The approach addresses one of the fundamental problems with machine learning: the necessity for training set to develop a model that generalizes provided examples. The inductive learning principle is still in effect for supervised algorithms. However, shrinking the size of the training data is an objective for many AI scientists. The ability to utilize smaller training data sets without compromising the quality of the model is essential.
https://www.wired.com/story/facebook-new-ai-teaches-itself-see-less-human-help/
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.