predictor
A neural network component in JEPA that takes the context embedding and attempts to produce the target embedding, learning to predict the representation of the next or missing observation
As defined in What Is Yann LeCun Cooking? JEPA Explained Simply
Where it comes up · 1
Most important claims · 4 of 4Search all claims for “predictor” →
- When views are compressed into latent space, the target embedding naturally removes all noise and contains only compressed abstraction and semantics, allowing the predictor to model only stable structure between views without noise interference.What Is Yann LeCun Cooking? JEPA Explained Simply
- Representation collapse is a failure mode where both the context and target encoders in JEPA can learn to output the same constant embedding for all inputs, with the predictor simply outputting a constant embedding that always matches, resulting in extremely low training loss but learning absolutely nothing about the world.What Is Yann LeCun Cooking? JEPA Explained Simply
- For complex JEPA applications, the latent space must be structured to support planning, with the predictor learning smooth transitions between states through conditional actions, so changes in latent state make sense and predicted trajectories don't drift or accumulate errors.What Is Yann LeCun Cooking? JEPA Explained Simply
- A typical JEPA learning setup contains three components: a context encoder that takes visible content and produces an embedding, a target encoder that takes masked or future content and produces a target embedding, and a predictor that takes the context embedding and tries to produce the target embedding.What Is Yann LeCun Cooking? JEPA Explained Simply