Concepts of Learning

Learning

Acquisition of knowledge or skill through the study, experience or being taught is understood as learning. The processing of new knowledge from the environment is also called as learning. A learning agent can be thought of containing a performance element which decides what action to take and a learning element that modifies the performance element so that it makes the better decision.

The different types of learning are listed below:

1. Supervised learning.
2. Unsupervised learning
3. Reinforcement learning
4. Learning by analogy
5. Learning by example
6. Explanation-based learning.

Supervised Learning

It is the machine based learning task of inferring a function from the labeled training data. The training data consists of a set of training examples. In supervised learning, each example is a pair which consists of an input object and the desired output value. The supervised learning algorithm analyzes a training data and produces an inferred function which can be used for the mapping of new examples. The optimal scenario will allow for the algorithm to determine the class labels correctly for the unseen instances. This requires the learning algorithm to generalize from the training data to the unseen situations in a "reasonable" way.

Unsupervised Learning

An unsupervised learning is the machine learning task of inferring a function in order to describe the hidden structure from unlabeled data. Since the examples given to the learners are unlabeled, there is no error or reward signal to evaluate the potential solution. This distinguishes the unsupervised learning from the supervised learning and the reinforcement learning.

Reinforcement Learning

The reinforcement learning is defined not by characterizing learning methods but characterizing a learning problem. Any method that is well suited for solving that problem we consider it to be the reinforcement learning method. The basic idea is simply to capture the most important aspects of the real problem facing a learning agent interacting with its environment to achieve a goal. Such an agent clearly must be able to sense the state of the environment to some extent and must be able to take actions that affect the state. The agent also must have a goal or goals related to the state of the environment.

Reinforcement learning is different from supervised learning. This is an important kind of learning but alone it is not adequate for learning from interaction. In interactive problems, it is often impractical to obtain examples of desired behavior that are both correct and representative of all the situations in which the agent has to act.

Learning by Analogy

It is a powerful mechanism that is used for exploiting the past experience in planning and problem solving. This process is developed to extract knowledge from past successful problem-solving situations that bear a strong similarity to the current problem. The analogy is one of the central inference methods in human cognition as well as a powerful computational mechanism.

Learning by Example

For an instance, the intelligent agent may have to learn the following components:

• The direct mapping from conditions on the current state to actions.
• The means to infer the relevant properties of the world from the perception sequence.
• Information about the ways which the world evolves and about the results of possible actions that the agent can take.
• Utility information indicating the desire of world states.
• The action-value information indicating the desire of actions.
• The goals that describes the classes of states whose achievement maximizes the agent’s utility.

Explanation-based Learning

An Explanation-based Learning (EBL) system accepts a training example and explains what it learns from the example. The EBL system takes only the relevant aspects of training. This explanation is translated into a particular form that a problem-solving program can understand. The explanation is generalized in such a way that it can be used to solve other problems.

References

1. Elaine Rich, Kevin Knight 1991, "Artificial Intelligence".
2. Nilsson, Nils J. Principles of Artificial Intelligence, Narosa Publishing House New Delhi, 1998.
3. Norvig, Peter & Russel, Stuart Artificial Intelligence: A modern Approach, Prentice Hall, NJ, 1995
4. Patterson, Dan W. Introduction to Artificial Intelligence and Expert Systems, Prentice Hall of India Private Limited New Delhi, 1998.