卷积神经网络和递归神经网络有什么区别? [英] What's the difference between convolutional and recurrent neural networks?
问题描述
我是神经网络领域的新手.我遇到了两个术语:卷积神经网络和递归神经网络.
I'm new to the topic of neural networks. I came across the two terms convolutional neural network and recurrent neural network.
我想知道这两个术语是否指的是同一件事，或者如果不是的话，它们之间有什么区别?
I'm wondering if these two terms are referring to the same thing, or, if not, what would be the difference between them?
推荐答案
CNN与RNN之间的区别如下:
Difference between CNN and RNN are as follows:
-
CNN采用固定大小的输入并生成固定大小的输出.
CNN takes a fixed size inputs and generates fixed-size outputs.
CNN是一种前馈人工神经网络-是多层感知器的变体，旨在使用最少的预处理.
CNN is a type of feed-forward artificial neural network - are variations of multilayer perceptrons which are designed to use minimal amounts of preprocessing.
CNN使用其神经元之间的连通性模式，并受到动物视觉皮层组织的启发，动物皮层的各个神经元以它们对覆盖视场的重叠区域做出响应的方式排列.
CNNs use connectivity pattern between its neurons and is inspired by the organization of the animal visual cortex, whose individual neurons are arranged in such a way that they respond to overlapping regions tiling the visual field.
CNN非常适合图像和视频处理.
CNNs are ideal for images and video processing.
RNN:
-
RNN可以处理任意输入/输出长度.
RNN can handle arbitrary input/output lengths.
RNN与前馈神经网络不同-可以使用其内部内存来处理任意输入序列.
RNN unlike feedforward neural networks - can use their internal memory to process arbitrary sequences of inputs.
递归神经网络使用时间序列信息.即我最后讲的内容会影响我接下来要讲的内容.
Recurrent neural networks use time-series information. i.e. what I spoke last will impact what I will speak next.
RNN非常适合进行文本和语音分析.
RNNs are ideal for text and speech analysis.
这篇关于卷积神经网络和递归神经网络有什么区别?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
