Fill in the blank. AI can use a process called$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$ to analyze only small parts of an image at a time, which makes it possible for visual recognition systems to identify things in an image.

vocal recognition network $($VRN$)$

generative adversarial network $($GAN$)$

natural language processing $($NLP$)$

convolutional neural network $($CNN$)$