LeNet-5

Fact

An early CNN built to read handwritten numbers.

In Plain Words

LeNet-5 is the old-school bank teller of AI. Even with wobbly check numbers, it can spot 0 through 9.

It was used for checks and ZIP code digits. It is still a starter example for learning CNNs.

Related Concepts

• Convolutional Neural Network
• Handwritten Digit Dataset
• AlexNet Convolutional Neural Network
• Backpropagation

CNN
LeNet-5 is a classic early CNN and showed the design could read images.

MNIST
MNIST made LeNet-5 a starter model for handwritten digits.

AlexNet
AlexNet followed the CNN path and scaled it up.

Backpropagation
LeNet-5 uses Backpropagation to learn its settings end to end.