> For the complete documentation index, see [llms.txt](https://vikram-bajaj.gitbook.io/deep-learning-specialization-coursera/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://vikram-bajaj.gitbook.io/deep-learning-specialization-coursera/main-10/convolutional-neural-networks/deep-convolutional-models-case-studies/resnet.md).

# ResNets

ResNets stands for Residual Networks. They were invented in 2015.

They introduced the concept of **skip-connections** that allow us to feed the activation of one layer to another layer deeper in the network. This, in turn, allows us to train significantly deeper neural networks.

![](https://3732905555-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M5-0RGo4dZhdwCIHrC1%2F-M5-0TEuN77zAmTpQjIr%2F-M5-0VoajrJ4wdxcq_R9%2Fskip%20connection.png?generation=1586990828081188\&alt=media)

ResNets are build out of **residual blocks**:

![](https://3732905555-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M5-0RGo4dZhdwCIHrC1%2F-M5-0TEuN77zAmTpQjIr%2F-M5-0VocTm3RwhNm3q_k%2Fresidual%20block.JPG?generation=1586990827940072\&alt=media)

Basically, the activation of one layer gets propagated to a deeper layer without passing through intermediate layers, and gets added to the output of the destination layer before ReLU is applied.

The following image shows a regular "plain" network vs. a residual network:

![](https://3732905555-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M5-0RGo4dZhdwCIHrC1%2F-M5-0TEuN77zAmTpQjIr%2F-M5-0VoeDf6MI4Csl1Ev%2FPlain%20vs.%20ResNet.JPG?generation=1586990828032945\&alt=media)