The course introduces the ideas and techniques underlying the principles and design of artificial intelligent systems. The course covers the basics and applications of AI, including: design of intelligent agents, problem solving, searching, knowledge representation systems, probabilistic reasoning, neural networks, machine learning and natural language processing.
CSC266Semester IV3 credit hours6 units72 solved questions941 study cardsFull study modes
The course introduces the ideas and techniques underlying the principles and design of artificial intelligent systems. The course covers the basics and applications of AI, including: design of intelligent agents, problem solving, searching, knowledge representation systems, probabilistic reasoning, neural networks, machine learning and natural language processing.
The free sample is open to everyone. Sign in for 2 free weeks of every answer, flashcards and progress.
This unit introduces artificial intelligence as a field of study: how the discipline is defined from four different angles, how it developed from the 1940s to the present, the other disciplines it draws its foundations from, and the areas where it is applied today.
Intelligence is the capacity to learn from experience, reason about a situation and solve problems that have not been seen before. Artificial Intelligence (AI) is the branch of computer science concerned with building systems that exhibit these characteristics, that is, systems that reason, plan, represent knowledge, learn, perceive and communicate in a way that would be called intelligent if a human did it. Work in AI therefore spans several closely related concerns: automated deduction, planning, problem solving, knowledge representation, learning, and natural language processing, each of which becomes its own unit later in this subject.
There is no single agreed definition of AI. Different researchers have framed the goal of the field along two independent axes: whether the system should think or act, and whether the standard it is measured against is human behaviour or an idealised standard of rationality. Crossing these two axes gives four perspectives.
Thinking humanly (the cognitive modelling approach). A program is said to think like a human only once we have a precise enough theory of how humans actually think and can express that theory as a program whose input-output behaviour matches human behaviour on the same task. A theory of mind of this kind can be built in three ways: through introspection (catching one's own thoughts as they occur), through psychological experiments (observing a person performing a task), and through brain imaging (observing the brain while it works).
Acting humanly (the Turing test approach). Alan Turing proposed that a computer can be called intelligent if a human interrogator, after posing written questions to both a computer and a person, cannot reliably tell which of the two answered. Passing this test would in practice require natural language processing (to communicate in English), knowledge representation (to store what it is told), automated reasoning (to answer questions and draw new conclusions from stored information), and machine learning (to adapt to new circumstances and detect patterns).
Thinking rationally (the "laws of thought" approach). Aristotle was among the first to try to codify correct reasoning through syllogisms, patterns that give a guaranteed correct conclusion from correct premises: "Socrates is a man; all men are mortal; therefore Socrates is mortal" is the standard example. This line of thought led to the field of formal logic, and the logicist tradition in AI tries to build intelligent systems directly on top of logical inference. Two obstacles limit this approach in practice: informal, uncertain knowledge is hard to state in the strict form logic requires, and there is a large gap between showing a problem is solvable "in principle" by logic and actually solving it efficiently.
Acting rationally (the rational agent approach). A rational agent acts so as to achieve the best expected outcome given what it perceives and what it knows; this is the definition used throughout this subject. Compared with the laws-of-thought approach, acting rationally is more general, since correct logical inference is only one of several possible routes to a good action, and it is more amenable to scientific development than approaches anchored to human behaviour or human thought, since rationality can be defined mathematically and independently of whether it resembles how people actually think.
Artificial Intelligence for TU BSc CSIT is covered here in full, from syllabus notes to solved past questions. This subject has 6 chapters mapped to the official syllabus, and 72 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 BSc CSIT Artificial Intelligence guide covers Introduction, Intelligent Agents, Problem Solving by Searching, Knowledge Representation, Machine Learning, Applications of AI, across 6 chapters. It includes model answers to 72 past exam questions, plus flashcards for quick revision.
Artificial Intelligence has 6 chapters mapped to the official syllabus.
Yes. Each of the 72 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.