deeplearning

12 ideas

Self-Supervised Learning

Labelled data is expensive, which makes benefiting from the current success in supervised learning unfeasible for smaller companies.

However, good representations can be learned without any task-specific information from raw data.

In self-supervised learning, labels are generated artificially. A common approach is to take multiple augmented views from the same source and contrast them to different sources.

Many papers have proven that simply increasing the similarity (decreasing the distance in the embedding space) of such views from the same source can lead to strong representations.

6 STASHED

3 LIKES

Variance-Invariance-Covariance Regularization for Self-Supervised Learning

arxiv.org

3 IDEAS

BENJAMIN FRANKLIN

Tell me and I forget

Teach me and I learn

Involve me and I remember

13 STASHED

9 LIKES

Methods of Learning

google.com

1 IDEA

β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ
β€Œ

❀️ Brainstash Inc.