卷积特征提取
From Ufldl
(→Fully Connected Networks) |
(→Locally Connected Networks) |
||
Line 31: | Line 31: | ||
== Locally Connected Networks == | == Locally Connected Networks == | ||
+ | |||
+ | 【原文】 | ||
One simple solution to this problem is to restrict the connections between the hidden units and the input units, allowing each hidden unit to connect to only a small subset of the input units. Specifically, each hidden unit will connect to only a small contiguous region of pixels in the input. (For input modalities different than images, there is often also a natural way to select "contiguous groups" of input units to connect to a single hidden unit as well; for example, for audio, a hidden unit might be connected to only the input units corresponding to a certain time span of the input audio clip.) | One simple solution to this problem is to restrict the connections between the hidden units and the input units, allowing each hidden unit to connect to only a small subset of the input units. Specifically, each hidden unit will connect to only a small contiguous region of pixels in the input. (For input modalities different than images, there is often also a natural way to select "contiguous groups" of input units to connect to a single hidden unit as well; for example, for audio, a hidden unit might be connected to only the input units corresponding to a certain time span of the input audio clip.) | ||
Line 45: | Line 47: | ||
解决这类问题的一种简单方法是对隐含单元和输入单元间的连接加以限制:每个隐含单元仅仅只能连接输入单元的一部分。例如,每个隐含单元仅仅连接输入图像的一小片相邻区域。(对于不同于图像输入的输入形式,也会有一些特别的连接到单隐含层的输入信号“连接区域”选择方式。如音频作为一种信号输入方式,一个隐含单元所需要连接的输入单元的子集,可能仅仅是一段音频输入所对应的某个时间段上的信号。) | 解决这类问题的一种简单方法是对隐含单元和输入单元间的连接加以限制:每个隐含单元仅仅只能连接输入单元的一部分。例如,每个隐含单元仅仅连接输入图像的一小片相邻区域。(对于不同于图像输入的输入形式,也会有一些特别的连接到单隐含层的输入信号“连接区域”选择方式。如音频作为一种信号输入方式,一个隐含单元所需要连接的输入单元的子集,可能仅仅是一段音频输入所对应的某个时间段上的信号。) | ||
网络部分连通的思想,也是受启发于生物学里面的视觉系统结构。视觉皮层的神经元就是局部接受信息的(即这些神经元只响应某些特定区域的刺激)。 | 网络部分连通的思想,也是受启发于生物学里面的视觉系统结构。视觉皮层的神经元就是局部接受信息的(即这些神经元只响应某些特定区域的刺激)。 | ||
- | |||
- | |||
- | |||
== Convolutions == | == Convolutions == |