M12.3 CONNECT THE MECHANISM
Build visual features from local operations
Stack a few convolution layers and you can tell a beagle from a cat with under 100,000 weights. Trace one network layer by layer, from LeNet to ResNet.
LESSON OVERVIEW14 min lesson
Lesson overview
Stack a few convolution layers and you can tell a beagle from a cat with under 100,000 weights. Trace one network layer by layer, from LeNet to ResNet.
What you’ll explore
- Convolutional networks stack shared filters and nonlinear transformations; residual designs support deeper computation, while classification still depends on data and evaluation.
GO TO THE SOURCE
Original explanations, connected to the research.
Gradient-Based Learning Applied to Document Recognition (LeCun, Bottou, Bengio & Haffner, 1998)ImageNet Classification with Deep Convolutional Neural Networks (Krizhevsky, Sutskever & Hinton, 2012)Very Deep Convolutional Networks for Large-Scale Image Recognition (Simonyan & Zisserman, 2014)Deep Residual Learning for Image Recognition (He, Zhang, Ren & Sun, 2015)Dive into Deep Learning — modern convolutional neural networksSuggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.