Difference between Backward and Forward chaining
Forward chaining starts with the available data and user inference rules to extract more data from an end-user until the goal is reached. The reasoning applied to this information to obtain a logical conclusion. It is a system given one or more condition in which system search and the rule knowledge base each condition and rules that correspond to the condition are selected that rule can generate new condition from the conclusion. In which facts are held in a working memory and condition action rules represent actions to take when specified facts occur in working memory it may add and delete facts from working memory.
It is based on the decision the initial state is fetched, then it is called backward chaining. Backward chaining is also called as a decision-driven or goal-driven inference technique. In Backward chaining, Reasoning is done in the backward direction the system selects a goal state and reason in the backward direction. In which we select a goal state and rules and the goal state as conclusion establishes sub-goal to be satisfied for all the goal state to be true and there is a condition to satisfy all the sub-goals and check whether the given initial state matches with the established ones.
Forward Chaining Backward chaining Forward chaining suitable for breadth first search. Backward chaining suitable for depth search. It begins with initial facts. It begins with some hypothesis goal. It may slow, because in which we tested all the rules. It may fast as compared to Forward chaining because it test fewer rules. It provides small amount of data in which we use to store large amount of information. It provides small amount of data in which we store small information. It is basically on primarily data driven. It is basically on goal driven. It follows Top down reasoning. It follows bottom-up reasoning. It contains small number of initial states but large number of conclusion. It contains small number of initial goals and large number of rules. It is suitable for data collection problem like planning monitoring. It is suitable for hypothesis problem like diagnosis. In which all data is available. In which data must be acquired.
Attention reader! Don’t stop learning now. Get hold of all the important Machine Learning Concepts with the Machine Learning Foundation Course at a student-friendly price and become industry ready.