The above figure is for the structure of (1)______________ f…
The above figure is for the structure of (1)______________ for image classification Image data is needed to be converted to a 2-dimensional matrix (28 rows x 28 columns = 768 pixels). Then, it is needed to be converted into a vector for 768-pixels. A fully connected layer means each input node in a layer is connected all output nodes in the next layer. Therefore, this model require high computation resources and time and cannot learn spatial information in the image data. * note: we call the fully connected layer an affine layer The above figure is for the structure of (2) _____________________for image classification. Image ref: https://github.com/WegraLee/deep-learning-from-scratch?tab=readme-ov-file
Read Details