3-4. Convolutional layer

In the convolution layer, the convolution operation of the input sample and the weight filter is performed.
Slide the filter at regular intervals and perform convolution processing on the whole．

After convolution, a bias (common value) is added, and the value passed through the activation function becomes the output value of the convolution layer..
If the input image is filtered and biased is $z_{\mathrm{cl}}^{\mathrm{uv,k\text{'}}}$ (weighted input)
If the activation function is $h\left(z\right)$. the unit output $a_{\mathrm{cl}}^{\mathrm{uv,k\text{'}}}$for $z_{\mathrm{cl}}^{\mathrm{uv,k\text{'}}}$is