Neural-network building blocks · MLD-1307
Vector-Jacobian product
A vector multiplied by a Jacobian, propagating output sensitivities backward.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Compute reverse-mode gradient contributions.
Original caveat
Input and output shapes determine the direction of the product.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · Vision · NLP.
Aliases: VJP.
Related concepts
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗