Topic: and preparation of sampling for training
Good afternoon, training for recognition of hand-written digits needs many pictures of each digit. If I want, that the digit was recognized turned on 90 degrees appropriate pictures are necessary at training. An operation principle if I correctly understand such that in network layers the coefficients, tutorings satisfying to sampling steal up. I.e. as though descent? Only it is not clear as to be, if it is necessary to learn to recognize digit on the big pictures where the digit can be at any angle and with any geometrical distortions (within recognition ). It is necessary for digit training under each corner to submit? And how if for one digit at training we submit tens , and it is necessary to search for inputs in the big picture on thousand ? I Am sorry, if a question silly.