AI GlossaryBackpropagationENTRY — Neural Networks
[Neural Networks]
Backpropagation.
The algorithm for calculating gradients of the loss function with respect to network weights.
In-depth explanation
01Backpropagation efficiently computes how each weight contributes to the overall error by propagating error signals backward through the network using the chain rule of calculus. Combined with gradient descent, it enables training of deep neural networks. The algorithm made modern deep learning possible and remains fundamental to neural network training.
Examples
02EX. 01
Training any neural network
More in Neural Networks
0301Activation FunctionA mathematical function that determines the output of a neuron based on its weighted input sum.02Batch SizeThe number of training examples used in one iteration of model training.03EpochOne complete pass through the entire training dataset during model training.04Neural NetworkA computing system inspired by biological neural networks, consisting of interconnected nodes (neurons).05NeuronA basic computational unit in a neural network that receives inputs, applies weights and activation, and produces output.
[NEXT] — APPLY THE CONCEPT
Master Backpropagation.
Learn how to apply this concept with hands-on projects in our comprehensive AI programs.