Tiven Wang
Wang Tiven July 11, 2018
425 favorite favorites
bookmark bookmark
share share

想要深入理解卷积神经网络,就要理解数学里卷积 (Convolution) 的概念,可以参见 Convolution,还可以阅读 Chris Olah’s blog post - Understanding Convolutions

Filters and Feature Maps

tf.nn.conv2d

tf.nn.max_pool

deep convolutional networks

Building blocks

Convolutional layer

神经元可以表示为

Pooling layer

ReLU layer

Fully connected layer

Loss layer

词汇

  • locally invariant 局部不变
  • fractional max pooling 分数最大池

References

Similar Posts

Comments

Back to Top