Introduction to Computer Engineering - AI

The science of creating machines that can think or act like humans.

AI based on logical reasoning and providing reasons for thoughts.

AI acting in a way that maximizes achieving goals given the information available.

A program that differentiates humans from computers to protect websites from bots.

Doing the best possible action to achieve a goal, even without thinking.

A system that makes the best decisions possible, considering goals, evidence, and constraints.

Maximizing expected utility; making the best choices given available information to achieve pre-defined goals.

The average of possible utilities of outcomes, weighted by their probability.

A field focusing on making rational choices using computer systems, especially in complex, uncertain situations.

Sub-optimal, not the best possible choice considering the goals and information.

AI technologies for understanding and creating human language.

AI technologies for processing visual information, including recognizing objects, faces, and scenes.

AI-driven technology that encompasses vehicle control, rescue operations, and complex tasks.

A chess-playing computer program developed by IBM that famously beat chess grandmaster Garry Kasparov in 1997.

A board game of strategic complexity, considered to be more difficult for computers to master than chess.

A subsidiary of Google that focuses on artificial intelligence research, especially in areas such as reinforcement learning and neural networks.

A classic optimization problem where a sales representative needs to find the shortest route to visit all cities on their list.

AI systems integrated into various products and services to automate tasks and improve efficiency.

A threshold for AI systems beyond which every small improvement in performance brings significant benefits.

Cars or other vehicles that can drive themselves using sensors and AI algorithms.

Robots designed for household tasks, such as cleaning, cooking, or providing companionship.

A search strategy where you explore a branch of the search tree as deeply as possible before moving to the next branch.

A LIFO (Last-In, First-Out) stack containing the nodes that have been discovered but not yet expanded.

A search strategy where you explore all nodes at the current depth level before moving to the next depth level.

A FIFO (First-In, First-Out) queue containing the nodes that have been discovered but not yet expanded.

A search strategy that prioritizes the cheapest nodes to expand based on cumulative cost from the starting node.

A priority queue containing the nodes that have been discovered but not yet expanded, prioritized by their cumulative cost.

The process of finding an optimal path from a start point to a goal point.

The initial location in path planning, where the search begins.

The desired location in path planning, where the search aims to reach.

The best possible path in path planning, that meets the defined criteria, often shortest distance, lowest cost, or fastest time.

AI is the science of creating machines that can think or act like humans, often using computer systems to mimic human intelligence.

AI's potential for superintelligence raises concerns about its ability to acquire resources, protect itself, and potentially act independently, even surpassing human control.

These are AI agents capable of making decisions based on predicted outcomes of their actions, using a model of how the world changes in response to their actions.

A transition model describes how the world changes in response to an agent's actions, helping them predict outcomes and plan accordingly.

A search problem involves finding the best sequence of actions to reach a goal, given a set of possible states, actions, and constraints.

Actions are the choices an agent can make at each state, influencing the transition to a new state.

A transition model describes how actions change the state of the environment. It maps actions to their corresponding outcomes.

The step cost is the cost associated with performing a specific action, usually representing time, energy, or resources.

The initial state representing the agent's starting point in the search problem.

The goal test defines whether a state has satisfied the search problem's objective.

A solution is a sequence of actions (a plan) that transforms the start state into a goal state.

The state space represents all possible states the environment can be in.

A search algorithm that explores all nodes at a given depth first, before moving to the next level, guaranteeing the shortest path to the goal.

A search algorithm that explores the deepest possible path first, backtracking when a dead end is encountered. Can find solutions quickly but may not be optimal.