Differences Between CNN and RNN in Deep Learning

Differences Between CNN and RNN in Deep Learning

by

CNN and RNN are the two most commonly used deep learning network structures in deep learning, and some students may still be unclear about the differences between these two networks.

Now let’s illustrate the specific applications of CNN and RNN with a diagram:

Differences Between CNN and RNN in Deep Learning

One to One: This represents the scenario of the CNN network, from fixed input to fixed output.

One to Many: This is the scenario of RNN, where the output is a sequence, similar to describing a picture, for example, fixing an input image and then outputting a sequence that describes the meaning of this image.

Many to One: This is the scenario of RNN, where the input is a sequence. For instance, when we perform sentiment analysis, we input a string of variable length and return the emotion.

Many to Many: This is also a scenario of RNN, commonly seen in sequence to sequence tasks. For example, using data from Jay Chou’s lyrics, we can mimic and write a song in Jay Chou’s style. In this scenario, both the input and output lengths are variable.

Source: 凡人机器学习. If there is any infringement, please contact the public account for adjustments.

Cover image source: Internet.

Welcome to visit the Traditional Chinese Medicine Clinical Intelligent Decision-Making System at http://www.tcmcds.com/

Differences Between CNN and RNN in Deep Learning

Differences Between CNN and RNN in Deep Learning

Differences Between CNN and RNN in Deep Learning

Differences Between CNN and RNN in Deep Learning

For more content, please scan the QR code below to follow us:

Differences Between CNN and RNN in Deep Learning

Institute of Chinese Medical Sciences, Chinese Academy of Traditional Chinese Medicine

Intelligent R&D Center for Traditional Chinese Medicine Health

Leave a Comment