Artificial Intelligence CNN Convolutional Neural Network How to share weights?
First of all weights sharing is filter sharing, the parameters of the filter are fixed, that is, the same filter to sweep the image once, to extract the feature features once, to get the featuremap. in the convolutional network, learning a filter is equivalent to mastering a kind of feature, this filter slides in the image, feature extraction, and then all the operations carried out in this way regions are captured with such a feature, as in the horizontal line above.
All convolutional kernels in the same convolutional layer in a convolutional neural network are weight sharing ()
All convolutional kernels in the same convolutional layer in a convolutional neural network are weight sharing ()
A.TRUE
B.FALSE
Correct Answer.
How to understand the weight sharing problem in AI neural networks?
The term weight (weight) sharing was introduced by the LeNet5 model. In the case of a CNN, for example, the parameters of the same convolution kernel are used during the convolution of a graph bias. For example, a 3×3×1 convolution kernel, the parameters of the 9 within this convolution kernel are shared by the entire image without changing the weight coefficients within the convolution kernel due to different positions within the image. To put it more bluntly, it is a convolutional kernel does not change the weight coefficients within the case of convolutional processing of the entire image (of course, each layer of CNN will not have only one convolutional kernel, this is just for the sake of convenient explanation only).