Machine LearningLesson 9Free preview

ML Recognition

This lesson is part of A.I. · All levels

Summary

Pattern recognition is the task of AI to recognize the shape, image, or sound of raw data. The image is converted into a pixel-number matrix so that it can be processed by a perceptron. The more patterns you want to identify, the more complex networks you need.

Key points

The image is expressed as a number matrix, generally pixels 0 (white) and 1 (black).
Perceptrons can be trained to recognize simple pixel patterns like lines or numbers.
Speech recognition is another branch of AI that's similar in principle.
Complex patterns require layered networking.

Full lesson

Code examples and quizzes

Full lessons, code examples, and quizzes are available to subscribers. 5 questions.