Intelligence does not imply perfect understanding, however, every intelligent being has limited perception both vision and speech, memory – understanding, problem solving, analytical ability and computation. Also other sensory channels such as, touch, taste, smell, hear, and voice.
Several in deed many points on the spectrum of intelligence versus coast are viable, from animals to human beings. Artificial Intelligence seeks to understand the computations required from intelligent behavior to produce intelligent computer systems-expert computer systems that exhibit knowledge – intelligence, knowledge exhibition, acquisition, extraction/ retrieval, and knowledge elicitation. Aspects of intelligence studied by AI includes perception – speech and vision, motor control, communication using human natural and spoken languages, reasoning, planning and collation, learning and memory understanding or understanding the memory.
Perception : The perception involves machine vision, speech understanding, tactile sensation and motor control as well.
Consider Machine Vision and Perception : The accurate machine vision opens up a new realm of computer applications. These applications include mobile robot navigation, complex manufacturing tasks, analysis of satellite images, image understanding, and medical image processing and understanding. It may be easy to interface a TV camera to a computer and get an image into memory, the problem understanding. Actually what the image represents and what kind of information that the image represents and what kind of information that we can extract from such complex image.
Speech Understanding : Spoken language is a more natural form of communication in several in deed many form of communication in many human computer interactions. Speech understanding is available now on personal computers. These systems must be trained for the individual user (human) and require pauses between words. Understanding continuous speech with a larger vocabulary is harder and harder.
Tactile Sensation : limited developments to date. Important for the robot assembly problems and tasks.
Robotics : Robots can process visual and auditory information, and they can also be equipped with more special sensors, such as laser range finders, path finders, speedometers, and radar communications. Though industrial robots to date have been expensive, robot hardware can be cheap. What is needed is perception and intelligence to tell robot effectors what to do, ‘billing’ robots are limited to very well designed and well structured tasks like spray painting car bodies, etc.
Natural Language: In natural language there comes three sub-areas, namely, NLU, NLG, and NLT.
Consider NLU : Natural languages are human languages such as English. Making computers understand English allows non-programmers to use them with little training. This is much more complicated than image understanding.
Then Consider NLG : making computers to generate human/ natural languages can be called as natural language generation . It is much earlier than the NLU.
NLT, i.e., MT: A text in one language say Sanskrit and then generate it in another language say Hindi by means of computers can be called as machine translation (MT). It is important for organizations that operate in many countries in many multilingual -lingua franca’s, and etc. In multi lingual areas this field is very very important, the natural language skills are also important given its widespread status across the globe as lingua francua.
Speech Recognition : Human speech recognition is easier than the computer speech recognition. For example, consider the following set of statements of natural spoken English language:
‘Meet her at the end of the street’ and
‘Meter at the end of the street’.
Here, accent does matter. Therefore, the speech recognition (i.e., computer) system doesn’t know which one to accept, thereby ambiguity.
Planning : planning attempts to order the application of resources to achieve the goals. Planning applications include logistics, manufacturing scheduling. Planning steps in manufacturing is to construct a desired product.
Expert Systems: expert systems attempt to capture the knowledge of a human expert and make it available through a computer program. For thin knowledge extraction, knowledge acquisition and elicitation are important.
Machine Learning: learning has remained a challenging areas of AL An expert system may perform costly computations to solve a particular problem. Unlike human beings it cannot remember the solution, if it is given the same problem for second time. One of the solution for these problems for programs is to learn on their own either from experience, examples or analogy, etc.
Cognitive Systems: Cognitive systems are those systems which can operate on mind games, such as chess games, checkers games, Go games, Tic-Tac-To games and etc.
Theorem Proving: proving mathematical theorems might seem to be mainly of academic interest. However, many practical problems can be cast in terms of theorems. A general theorem prover can therefore be widely applicable.
Symbolic Mathematics: it refers to manipulation of formulas, rather than doing arithmetic on numeric values. Some examples are, differential equations – differential calculus, integral equations – integral calculus/ predicate logic, prepositional and or propositional logic, algebra, etc.
Game Playing: authorizing financial transactions, configuring hardware and software, scheduling for manufacturing, the future prediction, and etc.