Programme d'apprentissage

Définition

xxxxxxx

Français

xxxxxxx

Anglais

learning program

Normal programs P produce the same output y each time they receive a particular input x. Learning programs are capable of improving their performance so that they may produce different (better) results on second or later times that they receive the same input x.

They achieve this by being able to alter their internal state, q. In effect, they are computing a function of two arguments, P(x | q) = y. When the program is in learning mode, the program computes a new state q' as well as the output y, as it executes.

In the case of supervised learning, in order to construct q', one needs a set of inputs x_i and corresponding target outputs z_i (i.e. you want P(x_i | q) = z_i when learning is complete). The new state function L is computed as:

L(P, q, ((x₁,z₁), ..., (x_n, z_n))) = q'

See also unsupervised learning, observation language, and hypothesis language.

Source : UNWS machine learning dictionary ]