Abstract
Abstract To illustrate the abilities of networks introduced in this chapter, we follow an example of optical character recognition (OCR). OCR is the process of (optically) scanning an image and interpreting this digital image so that the computer ‘understands’ its meaning. For example, if we scan an image of the letter A, than we would like to store a binary number 1000001 in the computer. This binary number is a standard representation for encoding the letter A in the American Standard Code for Information Interchange (ASCII). Once the letter is represented with this code, a program can use this code to infer meaning and use this to perform specific tasks, such as displaying a representation of the letter on screen, printing the letter with different fonts on paper, or to look up words made out of such letters in a dictionary. The transformation of the digital image representation to the representation of the meaning of the image on a computer is a very challenging engineering task.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
