I am researching on AI and its working. Whenever I try to search for AI algorithms, ML algorithms come up. Then, I read the differences between ML & AI. One of the key points mentioned was "AI is decision making" & "Machine learning is generating values and learn new things".

I come up with a conclusion that ML allows us to take generate some sort of values and using AI we can make decisions with those values.

But I am confused with "The weather forecast" problem. Our machine learning model will directly generate the decision that will it rain or not? Is our ML model lies in the AI domain or I am wrong? Help me!


1 Answer 1


Artificial Intelligence is a very broad area of Computer Science which is intertwined with many other fields, and someone might argue that its definition is the discipline that develops rationally acting systems.

When it comes to Machine Learning, the generally accepted definition is programming computers to perform a specific task without specific instructions about the problem.

Being that broad of a field, AI comprises Machine Learning problems, but the difference between the two areas relies on how you devise your system:

  • if you make use of problem-specific knowledge in your algorithm: you're outside the ML field;
  • if you formulate your problem in a general-enough manner and use a generic algorithm: most likely you're inside the ML field.

I'm sure you have already seen this image from Nvidia a million times already, but it's intuitive to understand what's the relationship between AI and ML: the latter is part of the former.

Nvidia explanations of relationships among AI, ML and DL

  • $\begingroup$ What is the difference between problem specific knowledge & problem formulation $\endgroup$ Commented Mar 15, 2020 at 8:49
  • $\begingroup$ The focus is mostly about the algorithm: in case the solving algorithm makes use of problem-specific knowledge (i.e. rules of chess) and it is tailored on it in order to provide the solution, that is AI; on the other hand, if you're able to encode such knowledge in a way the solving algorithm is actually generic (i.e. least squares minimization) and knows nothing about the domain, that is ML. $\endgroup$ Commented Mar 15, 2020 at 20:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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