Home »
Machine Learning/Artificial Intelligence
Uncertainty in Artificial Intelligence – A brief Introduction
In this tutorial, we will learn what uncertainty is, how it is related to Artificial Intelligence, and how it affects the knowledge and learning process of an Agent?
By Monika Sharma Last updated : April 15, 2023
Uncertainty arises when we are not 100 percent confident in our decisions.
What is Uncertainty in AI?
When we talk about perceiving information from the environment, then the main problem that arises is that there is always some uncertainty is our observations. This is because the world is an enormous entity and the surroundings that we take under study is not always well defined. So, there needs to be an estimation taken for getting to any conclusion.
Human being face this uncertainty daily that too many times. But still, they manage to take successful decisions. This is because humans have strong estimating and decision making power and their brains function in such a way that every time such a situation arises, the alternative with the maximum positive output is chosen. But, the artificial agents are not able to take proper decisions while working in such an environment. This is because, if the information available to them is not accurate, then they cannot choose the right decision from their knowledge base.
Uncertainty Example
Taking a real life example, while buying vegetables, humans can easily distinguish between the different kinds of vegetables by their color, sizes, textures, etc. But there is uncertainty in making the right choices here, because the vegetables may not be exactly the same as described. Some of them may be distorted, some may vary than the usual size and there can be many such variations. But in spite of all of them, humans do not face any problem in situations like these.
But, this same thing becomes a hurdle when the decision is to be made by a computer based agent. Because, we can feed the agent by the information that how the vegetables look, but still we cannot accurately define the exact shape and size of each of them, because all of them have some variations.
So, as a solution to this, only the basic information is provided to the agent. Based on this very information, the agent has to make certain estimates to find out which vegetable is kept in front of it.
Not only in this agent, but in designing almost every AI based agent, this strategy is followed. So, there should be a proper method so that the agent can make certain estimations by itself without any help or input from human beings.