What is Backpropagation?
ML Fundamentals
Backpropagation — The algorithm used to train neural networks. It calculates gradients of the loss function with respect to each weight by propagating errors backward through the network.
FAQ
What is backpropagation?
The algorithm that trains neural networks by calculating how much each weight contributed to the error, then adjusting weights to reduce error.
Why is backpropagation important?
It enables efficient training of deep networks with millions/billions of parameters. Without it, deep learning would not be practical.
Related Terms
Learn Backpropagation in depth
Free hands-on course with code examples and Google Colab notebooks.
Start Course →