Foundation Models Unpacked: How Self-Supervised Learning Solved the AI Data Bottleneck
Failed to add items
Add to basket failed.
Add to Wish List failed.
Remove from Wish List failed.
Follow podcast failed
Unfollow podcast failed
Foundation Models Unpacked: How Self-Supervised Learning Solved the AI Data Bottleneck
-
Narrated by:
-
By:
About this listen
Excerpts from the Stanford conferences and Yann LeCun's commentary offer an overview of the field of self-supervised learning (SSL), an emerging paradigm in artificial intelligence. The sources explain that SSL allows you to train large-scale deep learning models using untagged data, which addresses the limitation of the need for large-tagged data sets in traditional supervised learning. They discuss how SSL works by defining a pretext task where monitoring is automatically generated from input data, such as predicting missing parts of an image (as in Masked Autoencoders) or reordering patches (the Jigsaw puzzle). In addition, the concept of contrastive learning is presented, which trains models to generate similar representations for different views of the same object (positive pairs) and dissimilar representations for different objects (negative pairs). Once the model has been pre-trained with these tasks, its representations can be transferred to a later more specific task (such as classification or detection) with much less labeled data, using techniques such as fine-tuning or linear probing.