BIT252Semester IV10 units60 solved questions730 study cardsFull study modes
The free sample is open to everyone. Sign in for 2 free weeks of every answer, flashcards and progress.
Artificial intelligence is the study of making machines do tasks that need human intelligence. This chapter explains what AI is, how we test it, and how intelligent agents are described and built.
Artificial intelligence (AI) is the branch of computer science that builds machines able to think, learn, reason, and act in a useful way. The term was introduced by John McCarthy in 1956.
AI is described in four ways, depending on what we want the machine to copy:
| Approach | Meaning |
|---|---|
| Thinking humanly | Copy the human thought process (cognitive science) |
| Acting humanly | Behave so that people cannot tell it from a human (Turing test) |
| Thinking rationally | Reason by the laws of logic |
| Acting rationally | Do the best action for the goal (rational agent) |
The modern view is acting rationally. A machine is intelligent if it picks the action that gives the best expected result.
The scope of AI is wide. It includes problem solving, search, knowledge representation, reasoning, planning, learning, vision, speech, language processing, and robotics.
Alan Turing proposed the Turing test in 1950. A human judge talks by text with two hidden parties, one human and one machine. If the judge cannot tell which is the machine, the machine passes.
A machine needs these abilities to pass:
The total Turing test adds a video signal and objects to handle. So the machine also needs computer vision and robotics.
Is the test enough? Many people say no. A program can fool a judge with tricks and canned replies without understanding anything. John Searle's Chinese room argument says that following rules to manipulate symbols is not real understanding. The test also measures only human-like behaviour, not intelligence in general. A very smart machine that does not act like a human would fail.
Artificial Intelligence for TU BIT is covered here in full, from syllabus notes to solved past questions. This subject has 10 chapters mapped to the official syllabus, and 60 past exam questions with written model answers. The opening of every note and answer is free, and the most-searched questions are free in full. A free account gets 2 free weeks of the whole program plus flashcards and progress tracking so weak topics come back before the exam.
This TU BIT Artificial Intelligence guide covers Foundations of Artificial Intelligence, Agent Environments and Problem Formulation, Search Algorithms and Techniques, Knowledge Representation, Reasoning and Inference, Uncertainty and Probabilistic Reasoning, Expert Systems, Machine Learning and Neural Networks, and more, across 10 chapters. It includes model answers to 60 past exam questions, plus flashcards for quick revision.
Artificial Intelligence has 10 chapters mapped to the official syllabus.
Yes. Each of the 60 past questions comes with a written model answer; the most-searched ones are free in full, the rest open with a free account's 2 free weeks or a pass.
Free to start. The opening of every note and answer is free, the most-searched questions are free in full, and a free account gets 2 free weeks of the whole program plus flashcards and progress tracking. After that a program pass keeps everything open.
Based on the official syllabus.