Foundations of Artificial Intelligence

<p>Understanding decision-making processes (D)</p> Signup and view all the answers

<p>Regulatory Compliance (D)</p> Signup and view all the answers

<p>Strict regulatory measures (A)</p> Signup and view all the answers

<p>Defect Detection (A)</p> Signup and view all the answers

<p>Data collection and consent (C)</p> Signup and view all the answers

<p>f(n) = g(n) + h(n) (D)</p> Signup and view all the answers

<p>Simulated Annealing (C)</p> Signup and view all the answers

<p>Sentences that were not derived from other sentences (C)</p> Signup and view all the answers

<p>Genetic Algorithm (D)</p> Signup and view all the answers

<p>Adds new sentences to the knowledge base (D)</p> Signup and view all the answers

<p>Completeness (A)</p> Signup and view all the answers

<p>Greedy Best-First Search (C)</p> Signup and view all the answers

<p>A sentence true in at least one model (A)</p> Signup and view all the answers

<p>The development of computer systems able to perform tasks requiring human intelligence. (A)</p> Signup and view all the answers

<p>Narrow AI solves specific tasks while general AI can apply knowledge across various tasks. (C)</p> Signup and view all the answers

<p>An entity that can perceive its environment and act autonomously. (C)</p> Signup and view all the answers

<p>Reasoning, Learning, Problem Solving, and Perception. (B)</p> Signup and view all the answers

<p>Fashion Design (B)</p> Signup and view all the answers

<p>An agent that aims to achieve the best possible outcome based on knowledge and goals. (D)</p> Signup and view all the answers

<p>To find a solution that meets basic requirements without seeking the best outcome. (A)</p> Signup and view all the answers

<p>A chronological record of all data received by the agent from its sensors. (C)</p> Signup and view all the answers

<p>A* search with an admissible heuristic. (D)</p> Signup and view all the answers

<p>Problem Solving (D)</p> Signup and view all the answers

<p>No facts outside the known set can be true. (A)</p> Signup and view all the answers

<p>Dealing with the uncertainty of actions' outcomes. (C)</p> Signup and view all the answers

<p>The agent may encounter stochastic outcomes from actions. (B)</p> Signup and view all the answers

<p>To find a valid plan from a graph of partial plans. (A)</p> Signup and view all the answers

<p>It seeks to identify the best possible solution as per specific criteria. (D)</p> Signup and view all the answers

<p>The reliability of action outcomes. (A)</p> Signup and view all the answers

<p>To maximize rewards over time. (C)</p> Signup and view all the answers

<p>The agent learns to evaluate a fixed policy only. (D)</p> Signup and view all the answers

<p>To visit states that have not been adequately studied. (B)</p> Signup and view all the answers

<p>The agent learns both the policy and the value function. (C)</p> Signup and view all the answers

<p>Always selecting the action currently believed to be the best. (B)</p> Signup and view all the answers

<p>It determines the value of applying an action in that state. (A)</p> Signup and view all the answers

<p>The points earned for reaching a particular state. (D)</p> Signup and view all the answers

<p>The agent may never explore certain states due to sticking to one policy. (B)</p> Signup and view all the answers

<p>It is true in all models of the environment. (C)</p> Signup and view all the answers

<p>Set of objects, functions, and relations. (C)</p> Signup and view all the answers

<p>Planning identifies tasks while scheduling identifies the timing of those tasks. (A)</p> Signup and view all the answers

<p>Domain Specific planning is tailored for particular problems within specific domains. (A)</p> Signup and view all the answers

<p>Constant Symbols (A)</p> Signup and view all the answers

<p>Making autonomous decisions to achieve goals. (B)</p> Signup and view all the answers

<p>A logical expression that refers to an object. (B)</p> Signup and view all the answers

<p>Decision-making algorithms for stock trading. (B)</p> Signup and view all the answers

Conversion of images and videos into numerical arrays to enable machine learning tasks.

A method that compares data to a predefined value for decision making or classification.

AI systems can unintentionally reflect and amplify existing biases in the data they are trained on.

Understanding how AI systems make decisions, even if they are complex.

Ensuring that individual data privacy is protected when using AI.

Determining who is responsible when AI systems make mistakes or cause harm.

A regulation that classifies AI applications based on their risks and sets rules for transparency and compliance.

The process of acquiring, organizing, and analyzing data to extract meaningful insights.

A valid sentence in first-order logic (FOL) that is true in all possible interpretations of the symbols.

In FOL, it represents a collection of objects, functions, and relationships that describe the environment.

A logical expression in FOL that refers to an object.

A symbol that directly refers to a specific object in FOL.

A function in FOL that maps from an object to another object, representing a property of that object.

A placeholder for an object in FOL, allowing us to talk about objects in general.

The process of devising a strategy to achieve a goal by choosing actions that maximize the chances of success.

The process of deciding when to perform the actions identified in the planning stage.

The branch of computer science focused on creating machines that can perform tasks typically requiring human intelligence, like problem-solving, learning, and decision-making.

AI systems designed to solve specific tasks, like playing chess, recognizing speech, or identifying faces. They require reconfiguration or new algorithms to perform different tasks.

AI systems capable of understanding, learning, and applying knowledge across a wide range of tasks, just like humans.

Anything that can perceive its environment through sensors and act upon that environment through actuators.

An agent that acts autonomously to achieve goals based on observations and reasoning. It makes decisions to maximize its performance.

The complete history of all the data an agent has received from its sensors.

A system judged by its actions, aiming to perform tasks effectively.

An agent that aims to achieve the best possible outcome based on its knowledge and goals. It makes decisions to maximize its performance according to specific criteria.

The process of an agent learning from its interactions with the environment. It involves observing the effects of actions and adjusting its behavior to maximize rewards.

A mathematical framework for making decisions in situations with uncertain outcomes, aiming to maximize rewards over time. It involves defining states, actions, transitions, and rewards.

A type of reinforcement learning where the agent learns the value of a fixed policy without changing it. It focuses on evaluating how good a pre-determined set of actions is.

A type of reinforcement learning where the agent learns both the optimal policy and the value function. It explores the environment to find the best actions to maximize rewards.

A technique in active reinforcement learning where the agent always chooses the action that it believes will give the most reward, based on its current knowledge. This can lead to quick but potentially suboptimal results.

The challenge faced by reinforcement learning algorithms in balancing between exploring new, unanalyzed states and exploiting known, potentially optimal states.

A planning strategy that focuses on finding a solution that meets the basic requirements of the problem, even if it's not the most efficient or ideal solution.

A planning strategy that aims to find the best possible solution, considering factors like the fewest steps or minimal cost, even if it takes longer to compute.

A planning approach that deals with uncertainty in the environment or the outcomes of actions. It involves creating plans for different possible situations and using conditional statements to adjust the plan based on real-time information.

A state representation in AI planning where facts can be either true or false, and the current state is represented by the set of true facts. It assumes that everything not explicitly stated as true is false.

The simplest form of representation used in AI planning, often implemented using propositional logic, where facts are either true or false.

The problem of whether actions will always have the same outcome, or if there's randomness involved.

The problem of how much information about the current state is available to the planning agent.

The problem of dealing with other intelligent agents that might be present in the environment, who may have their own goals and could potentially interfere with or conflict with the planning agent's plans.

An informed search algorithm where each node is expanded based on a heuristic function estimating the cost to reach the goal. The node with the lowest estimated total cost is chosen for expansion.

A search algorithm that utilizes a heuristic function to assess the desirability of expanding nodes. It prioritizes nodes with the lowest estimated heuristic values.

A powerful search technique that combines the space efficiency of depth-first search (DFS) with the heuristic guidance of A*. It systematically performs depth-limited searches, increasing the depth limit until a solution is found.

A class of algorithms that explore the solution space (possible solutions) instead of the state space (possible states). They are typically used to find optimal solutions for optimization problems.

A local search algorithm that repeatedly moves to a neighboring state with the highest improvement in a heuristic function. It aims to find a local maximum, but may not reach the global optimum.

A local search algorithm that uses a probabilistic approach to escape local maxima. It starts with a high temperature and gradually cools down. At higher temperatures, the algorithm allows worse moves, preventing it from getting stuck.

A population-based optimization algorithm that simulates the evolution of candidate solutions. It uses processes like selection (choosing fitter solutions), crossover (combining solutions), and mutation (randomly altering solutions) to evolve towards a better solution.

A local search technique that maintains a fixed number of the most promising nodes at each level of the search tree. It prunes away less promising paths, making it efficient but potentially missing optimal solutions.