-1
$\begingroup$

The definition : A computer program is said to learn from experience E with respect to some task T and performance measure P, if its performance at task T, as measured by P, improves with experience E.

Here, we talk about what it means for a program to learn rather than a machine, and a program and a machine aren't equivalent so how can we use this as a definition of machine learning when its a definition of program learning.

Improve this question
$\endgroup$
1
  • 5
    $\begingroup$ Hi. Welcome to cross validated. This question is likely more appropriate for the Philosophy SE, The AI SE, or the Theoretical Computer Science SE. The short answer to your question is: Programs are always run on machines, and in the abstract, every program or algorithm corresponds to a Turing machine - which is a highly abstract model of how computers work in general. Hence conflating "Machine Learning", "Algorithmic Learning", "Program Learning", etc... makes sense. $\endgroup$
    – Skander H.
    Commented Feb 20, 2019 at 22:49

1 Answer 1

Reset to default
2
$\begingroup$

From Wikipedia, a computer program is a set of instructions used to control the behavior of a machine.

In my not philosophically trained opinion, the same way that we don't make a distinction between a human learning and a human's brain learning we don't make a distinction between a program learning vs a machine learning.

Improve this answer
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.