Learning of AI Systems

Learning is the enhancement of performance with experience over time. Learning element is the most important part of an Artificial Intelligence (AI) system that decides how to reform the performance element and implements those variations or modifications.

We all learn new knowledge through different procedures, depending on the type of material to be learned, the volume of pertinent or relevant knowledge we already have, and the environment in which the learning takes place.

Methods of Learning

There are five methods of learning . They are,

  1. Memorization (rote learning)
  2. Direct instruction (by being told)
  3. Analogy
  4. Induction
  5. Deduction

Rote Learning: Learning by memorizations is the simplest from of learning. It requires the least amount of inference and is practiced by simply copying the knowledge in the same form that it will be used directly into the knowledge base. Example:- Memorizing multiplication tables, formulate , etc.

Each time a new and useful piece of information is encountered, it is stored for future use. For example, an AI system might be designed to recognize faces by extracting a variety of features (such as distance between the eyes) from an image and searching for a match within a database of 1000 or more stored feature sets. If it observe a match, it has recognized the person; if not, it announce “unknown person.” In this latter case, the person or some human operator can provide the required details of this unknown person, and the system can enter the details in its database so that next time this person is presented to the system he or she will be accurately recognized.

Rote learning technique can also be used in complex learning systems provided sophisticated techniques are employed to use the stored values faster and there is a generalization to keep the number of stored information down to a manageable level.

The idea is that one will be able to quickly recall the meaning of the material the more one repeats it. Some of the alternatives to rote learning include meaningful learning, associative learning, and active learning. For example: Checkers-playing program uses this technique to learn the board positions it evaluates in its look-ahead search.

Direct instruction is a complex form of learning. This type of learning requires more inference than rote learning since the knowledge must be transformed into an operational form before learning when a teacher presents a number of facts directly to us in a well organized manner.

Analogical learning is the process of learning a new concept or solution through the use of similar known concepts or solutions. We use this type of learning when solving problems on an exam where previously learned examples serve as a guide or when make frequent use of analogical learning. This form of learning requires still more inferring than either of the previous forms. Since difficult transformations must be made between the known and unknown situations. For Example: We try to learn how to drive a bus while using our knowledge of driving a car.

Learning by induction is also one that is used frequently by humans. It is a powerful form of learning like analogical learning which also requires more inferring than the first two methods. This learning requires the use of inductive inference, a form of invalid but useful inference. We use inductive learning of instances of examples of the concept. For example: we learn the concepts of color or sweet taste after experiencing the sensations associated with several examples of colored objects or sweet foods.

Deductive learning is accomplished through a sequence of deductive inference steps using known facts. From the known facts, new facts or relationships are logically derived. Deductive learning usually requires more inference than the other methods. For Example: We could learn deductively that Neha and Meenu are cousin’s, if we have the knowledge of Neha and Meenu’s parents and rules for the cousin relationship.

Learning: Introduction and Overview - ppt download

Learning By Taking Advice

This is a simple form of learning. Suppose a programmer writes a set of instructions to instruct the computer what to do, the programmer is a teacher and the computer is a student. Once learned (i.e. programmed), the system will be in a position to do new things. The advice may come from many sources: human experts, internet to name a few. This type of learning requires more inference than rote learning. The knowledge must be transformed into an operational form before stored in the knowledge base. Moreover the reliability of the source of knowledge should be considered.

Learning by Problem Solving

In this type of learning there is no teacher advice but the learning is by experience. It does not involve increase in knowledge just method of using knowledge. For an intelligent agent to be fully autonomous and adaptive, all aspects of intelligent processing from perception to action must be engaged and integrated. To make the research tractable, a good approach is to address these issues in a simplified micro-environment that nevertheless engages all the issues from perception to action. We describe a domain independent and scalable representational scheme and a computational process encoded in a computer program called LEPS (Learning from Experience and Problem Solving) that addresses the entire process of learning from the visual world to the use of the learned knowledge for problem solving and action plan generation.

Problem solving in games such as Sudoku, can be done by building an AI system to solve that particular problem. To do this, one needs to define the problem statement first and then generating the solution by keeping the condition in mind. Some of the most popularly known problem solving things with AI are Chess, Travelling Salesman Problem, Tower of Hanoi, N-Queen Problem.

Problem Searching: In general, searching refers to as finding information one needs. Searching is the most commonly used technique of problem solving in AI.

The process of solving a problem consists of five steps as follows:

  1. Define the Problem
  2. Analyze the Problem
  3. Identification of Solution
  4. Choosing the Solution
  5. Implementation

Learning from Examples

Learn general concepts or categories from examples.

Leave a Reply

Your email address will not be published. Required fields are marked *