Explanation based learning is a technique in which a computer system is able to learn by being given explanations of the desired output. This type of learning is often used when it is difficult or impossible to write explicit rules that would produce the desired results.
For example, if a text analytics system were being trained to identify named entities such as people, organizations, and locations, it might be difficult to write rules that would cover all the possible ways that these entities could be expressed in text. However, it would be relatively easy to provide a few examples of each type of entity along with an explanation of why they should be considered as such. The system could then use these examples and explanations to learn how to identify other instances of these entities.
Outside of the text analytics industry, explanation based learning is also used in other areas such as artificial intelligence and machine learning. In these fields, it is often used in conjunction with other techniques such as rule-based learning or neural networks.
Explanation based learning should not be confused with other similar terms such as rule-based learning or example-based learning. Rule-based learning is a technique in which a system learns by being given a set of rules to follow. Example-based learning is a technique in which a system learns by being given a set of examples. Explanation based learning is different in that it relies on explanations of the desired output rather than rules or examples.
Benefits of Explanation based learning
There are several benefits to using explanation based learning. First, it can be used when it is difficult or impossible to write explicit rules that would produce the desired results. This is because the system can learn by being given explanations of the desired output. Second, explanation based learning can be used in conjunction with other techniques such as rule-based learning or neural networks. This allows for a more powerful and flexible learning system. Finally, explanation based learning should not be confused with other similar terms such as rule-based learning or example-based learning. Explanation based learning is different in that it relies on explanations of the desired output rather than rules or examples.