The general learning model involves an environment providing input to a learner, which uses the input to create and modify knowledge structures. The knowledge is then used by a performance component to complete tasks. A critic evaluates the performance and provides feedback to the learner to further modify its knowledge base. The goal is for the system's performance to improve through repetitive learning cycles.
The general learning model involves an environment providing input to a learner, which uses the input to create and modify knowledge structures. The knowledge is then used by a performance component to complete tasks. A critic evaluates the performance and provides feedback to the learner to further modify its knowledge base. The goal is for the system's performance to improve through repetitive learning cycles.
The general learning model involves an environment providing input to a learner, which uses the input to create and modify knowledge structures. The knowledge is then used by a performance component to complete tasks. A critic evaluates the performance and provides feedback to the learner to further modify its knowledge base. The goal is for the system's performance to improve through repetitive learning cycles.
The general learning model involves an environment providing input to a learner, which uses the input to create and modify knowledge structures. The knowledge is then used by a performance component to complete tasks. A critic evaluates the performance and provides feedback to the learner to further modify its knowledge base. The goal is for the system's performance to improve through repetitive learning cycles.
Learning can be accomplished using a number of different methods, such as by
memorization facts, by being told, or by studying examples like problem solution. Learning requires that new knowledge structures be created from some form of input stimulus. This new knowledge must then be assimilated into a knowledge base and be tested in some way for its utility. Testing means that the knowledge should be used in performance of some task from which meaningful feedback can be obtained, where the feedback provides some measure of the accuracy and usefulness of the newly acquired knowledge.
General learning model is depicted in figure above.
The environment has been included as a part of the overall learner system. The environment may be regarded as either a form of nature which produces random stimuli or as a more organized training source such as a teacher which provides carefully selected training examples for the learner component. The actual form of environment used will depend on the particular learning paradigm. In any case, some representation language must be assumed for communication between the environment and the learner. The information conveyed to the learner component is used to create and modify knowledge structures in the knowledge base. This same knowledge is used by the performance component to carry out some tasks, such as solving a problem playing a game or classifying instances of some concept given a task, the performance component produces a response describing its action in performing the task. The critic module then evaluates this response relative to an optimal response. Feedback, indicating whether or not the performance was acceptable, is then sent by the critic module to the learner component for its subsequent use in modifying the structures in the knowledge base. If proper learning was accomplished, the system’s performance will have improved with the changes made to the knowledge base. The cycle described above may be repeated a number of times until the performance of the system has reached some acceptable level, until a known learning goal has been reached, or until changes ceases to occur in the knowledge base after some chosen number of training examples have been observed. There are several important factors which influence a system’s ability to learn in addition to the form of representation used. They include the types of training provided, the form and extent of any initial background knowledge, the type of feedback provided, and the learning algorithms used. The type of training used in a system can have a strong effect on performance, much the same as it does for humans. In this model, the purpose of a learning machine is to be able to infer certain facts of some data X from a training set selected from X. Example: Over the set of all people we wish to automatically distinguish some person as either male or female based on a collection of n observations such as height, weight, pitch of voice, etc. We stack these observations into a feature vector x. If we have chosen the types of these observations intelligently then the distributions of these characteristics may tell us how to classify some person described by x. Example: Males will on average be taller, heavier, and have a lower pitched voice than females. So based on some instance of these characteristics, the hope is that we will be able to predict the sex of a subject with some amount of certainty. Deductive Learning and Inductive Learning Deductive learning Deductive learning works on existing facts and knowledge and deduces new knowledge from the old. This is best illustrated by giving an example. For example, assume: A=B B=C Then we can deduce with much confidence that: C=A Arguably, deductive learning does not generate "new" knowledge at all, it simply memorizes the logical consequences of what is known already. This implies that virtually all mathematical research would not be classified as learning "new" things. However, regardless of whether this is termed as new knowledge or not, it certainly makes the reasoning system more efficient. Inductive learning Inductive learning takes examples and generalizes rather than starting with existing knowledge. For example, having seen many cats, all of which have tails, one might conclude that all cats have tails. This is an unsound step of reasoning but it would be impossible to function without using induction to some extent. In many areas it is an explicit assumption. There is scope of error in inductive reasoning, but still it is a useful technique that has been used as the basis of several successful systems.
Procedural Knowledge and Declarative Knowledge
Procedural Knowledge (Imperative Knowledge): Describes how to do things, provides a set of directions of how to perform certain tasks, e.g., how to drive a car. Procedural knowledge consists of courses of action.
Declarative knowledge: It describes objects, rather than processes.
What is known about a situation, e.g. it is sunny today, and cherries are red. Declarative knowledge consists of facts about objects, events and situations.