backpropagation
Sign in to saveIn machine learning, backpropagation is a gradient computation method commonly used for training a neural network in computing parameter updates.
Article
23 sectionsContents
- Overview
- Matrix multiplication
- Adjoint graph
- Intuition
- Motivation
- Learning as an optimization problem
- Derivation
- Finding the derivative of the error
- Second-order gradient descent
- Loss function
- Assumptions
- Example loss function
- Limitations
- History
- Precursors
- Modern backpropagation
- Early successes
- After backpropagation
- See also
- Notes
- References
- Further reading
- External links
In machine learning, backpropagation is a gradient computation method commonly used for training a neural network in computing parameter updates.
It is an efficient application of the chain rule to neural networks. Backpropagation computes the gradient of a loss function with respect to the weights of the network for a single input–output example, and does so efficiently, computing the gradient one layer at a time, iterating backward from the last layer to avoid redundant calculations of intermediate terms in the chain rule; this can be derived through dynamic programming.