What is the difference between a Residual Neural Net and a Recurrent Neural Net?

As I understand,

Residual Neural Networks are very deep networks that implement 'shortcut' connections across multiple layers in order to preserve context as depth increases. Layers in a residual neural net have input from the layer before it and the optional, less processed data, from X layers higher. This prevents early or deep layers from 'dying' due to converging loss.

Recurrent Neural Networks are networks that contain a directed cycle which when computed is 'unrolled' through time. Layers in recurrent neural network have input from the layer before it and the optional, time dependent extra input. This provides situational context for things like natural language processing.

Therefor, a recurrent neural network can be used to generate a basic residual network if the input remains the same with respect to time.

Is this correct?


The answer is YES, they basically are the same according to this paper

enter image description here

The figure above shows how they compared both and how a ResNet can be reformulated into a recurrent form tat is almost identical to a RNN.
For more info you can read the paper and get deeper.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.