Backpropagation
Defined in 4 lectures. Each definition is in that lecture's terms.
Definitions are written by AI from each lecture’s transcript. The time opens the lecture where the lecturer explains it.
- Backpropagation is an algorithm that allows you to efficiently evaluate the gradient of a loss function with respect to the weights of a neural network.0:56Spelled-Out Intro to Neural Networks & Backpropagation: Building microgradAndrej Karpathy · Independent / Eureka Labs
- An algorithm that enables multi-layer perceptrons to be trained by propagating a gradient backward through multiple layers.
- An algorithm for propagating shared gradient terms efficiently throughout a computation graph using dynamic programming.
- Widely used training algorithm to adjusts neural-network weights.