AI is a vast field for research and it has got applications in almost all possible domain. By keeping this in mind, research in AI has focussed mainly on the following components of AI:
Learning is a very essential part of AI and it happens in a number of different forms. The simplest form of learning is by trial and error. In this form, the program remembers the section that has given the desired output and discards the other trial actions and learns by itself. For example, in chess (program) mate-in-one chess problems might try out moves at random until one is found that achieves mate. Here the program remembers the successful move and next time the computer is given the same problem it is able to produce the result instantly. It is also called unsupervised learning. The simple learning of individual items - solutions to problems, worlds of vocabulary, etc. is known as rote learning. In the case of rote learning, the program simply remembers the problem solution pairs or individual items. In other cases, a solution to few of the problems is given as input to the system, the basis on which the system or program needs to generate solutions for new problems. This is known as supervised learning.
2. Reasoning
Reasoning is also called as logic or generating judgments from the given set of facts. The reasoning is carried out based on a strict rule of validity to perform a specified task. Reasoning can be of two types, deductive or inductive. The deductive reasoning is in which the truth of the premised guarantees the truth of the conclusion while, in case of inductive reasoning, the truth of the premises supports the conclusion but it cannot be fully dependent on the premises. In programming logic generally, deductive inferences are used. Reasoning involves drawing inferences that are relevant to the given problem or situation.
3. Problem Solving
AI addresses a huge variety of problems. For example, finding out winning moves on the board games, planning actions in order to achieve the defined task, identifying various objects from given images, etc. Problem-solving methods are mainly divided into two types special-purpose and general-purpose methods. General purpose methods are applicable to a wide range of problems one used in AI is means-end analysis, which involves the step-by-step reduction of the difference between the current state and the goal state. Special purpose methods are customized to solve a particular type of problems.
4. Perception
In order to work in the environment, intelligent agents need to scan the environment and the various objects in it by means of different sense-organs, real or artificial. Agent scans the environment using sense organs like camera, temperature sensor, etc. This is called perception. After capturing various scenes, perceiver analyses the different objects in it and extracts their features and relationships among them.
5. Knowledge representation
The information obtained from the environment through sensors may not be in the format required by the system. Hence, it needs to be represented in standard formats for further processing like learning various patterns, deducing inference, comparing with past objects, etc. There are various knowledge representation techniques like Prepositional logic and First-order logic.
6. Language understanding
Natural Language Processing, involves machines or robots to understand and process the language that human speaks, and infer knowledge from the speech input. It also involves the active participation from a machine in the form of dialog i.e. NLP aims at the text or verbal output from the machine or robot. The input and output of an NLP system can be speech and written text respectively.
- Learning
- Reasoning
- Problem Solving
- Perception
- Knowledge representation
- Language understanding.
Learning is a very essential part of AI and it happens in a number of different forms. The simplest form of learning is by trial and error. In this form, the program remembers the section that has given the desired output and discards the other trial actions and learns by itself. For example, in chess (program) mate-in-one chess problems might try out moves at random until one is found that achieves mate. Here the program remembers the successful move and next time the computer is given the same problem it is able to produce the result instantly. It is also called unsupervised learning. The simple learning of individual items - solutions to problems, worlds of vocabulary, etc. is known as rote learning. In the case of rote learning, the program simply remembers the problem solution pairs or individual items. In other cases, a solution to few of the problems is given as input to the system, the basis on which the system or program needs to generate solutions for new problems. This is known as supervised learning.
2. Reasoning
Reasoning is also called as logic or generating judgments from the given set of facts. The reasoning is carried out based on a strict rule of validity to perform a specified task. Reasoning can be of two types, deductive or inductive. The deductive reasoning is in which the truth of the premised guarantees the truth of the conclusion while, in case of inductive reasoning, the truth of the premises supports the conclusion but it cannot be fully dependent on the premises. In programming logic generally, deductive inferences are used. Reasoning involves drawing inferences that are relevant to the given problem or situation.
3. Problem Solving
AI addresses a huge variety of problems. For example, finding out winning moves on the board games, planning actions in order to achieve the defined task, identifying various objects from given images, etc. Problem-solving methods are mainly divided into two types special-purpose and general-purpose methods. General purpose methods are applicable to a wide range of problems one used in AI is means-end analysis, which involves the step-by-step reduction of the difference between the current state and the goal state. Special purpose methods are customized to solve a particular type of problems.
4. Perception
In order to work in the environment, intelligent agents need to scan the environment and the various objects in it by means of different sense-organs, real or artificial. Agent scans the environment using sense organs like camera, temperature sensor, etc. This is called perception. After capturing various scenes, perceiver analyses the different objects in it and extracts their features and relationships among them.
5. Knowledge representation
The information obtained from the environment through sensors may not be in the format required by the system. Hence, it needs to be represented in standard formats for further processing like learning various patterns, deducing inference, comparing with past objects, etc. There are various knowledge representation techniques like Prepositional logic and First-order logic.
6. Language understanding
Natural Language Processing, involves machines or robots to understand and process the language that human speaks, and infer knowledge from the speech input. It also involves the active participation from a machine in the form of dialog i.e. NLP aims at the text or verbal output from the machine or robot. The input and output of an NLP system can be speech and written text respectively.