How did Arthur Samuel improve his checkers program so that it could learn from experience?

Created from Britannica articles using AI. AI can make mistakes, so verify using Britannica articles.

Artificial intelligence — artificial intelligence Image generated by the Stable Diffusion model from the prompt “the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings,” which is the definition of artificial intelligence in the *Encyclopædia Britannica* article on the subject. Stable Diffusion is trained on a large set of images paired with textual descriptions and uses natural language processing to generate an image.

Arthur Samuel improved his checkers program by incorporating mechanisms for both rote learning and generalization, which allowed the software to learn from experience.1

While Samuel initially based his 1952 program on the work of Christopher Strachey, he significantly extended its capabilities over several years. By adding these specific learning features in 1955, the program evolved to the point where it could successfully compete against human players, eventually defeating a former Connecticut checkers champion in 1962. These advancements represent a foundational milestone in the development of machine learning.1