Artificial Intelligence Course Quiz

<p>Knowledge-based systems. (A)</p> Signup and view all the answers

<p>Search algorithms. (D)</p> Signup and view all the answers

<p>Artificial neural networks. (C)</p> Signup and view all the answers

<p>Genetic algorithms. (A)</p> Signup and view all the answers

<p>Systems that can mimic human decision-making and responses. (B)</p> Signup and view all the answers

<p>Introduction to concepts in Artificial Intelligence and Machine Learning (D)</p> Signup and view all the answers

<p>Natural Language Processing (C)</p> Signup and view all the answers

<p>Both supervised and unsupervised learning techniques (C)</p> Signup and view all the answers

<p>Philosophical fundamental problems and ethical questions related to AI/ML (D)</p> Signup and view all the answers

<p>Computer Hardware Design (C)</p> Signup and view all the answers

<p>Practical understanding through implementations of methods (C)</p> Signup and view all the answers

<p>Artificial Neural Networks (A)</p> Signup and view all the answers

<p>Undergraduate - Level 3 (B)</p> Signup and view all the answers

<p>Competitive multiagent environment (B)</p> Signup and view all the answers

<p>Unique successor state given current state and action (A)</p> Signup and view all the answers

<p>Episodic experiences are independent and unconnected decisions (D)</p> Signup and view all the answers

<p>The agent's performance score (C)</p> Signup and view all the answers

<p>Word jumble solver (C)</p> Signup and view all the answers

<p>Dynamic continuous environment (A)</p> Signup and view all the answers

<p>Familiarity with the transition model (B)</p> Signup and view all the answers

<p>A fixed number of percepts and actions (C)</p> Signup and view all the answers

<p>Place children of CS in NSL, then add CS to SL. (C)</p> Signup and view all the answers

<p>DE holds nodes that have been completely processed. (A)</p> Signup and view all the answers

<p>CS is immediately added to DE and removed from SL. (C)</p> Signup and view all the answers

<p>If CS has no children. (C)</p> Signup and view all the answers

<p>To facilitate the backtracking process. (B)</p> Signup and view all the answers

<p>The sequence of actions with the lowest path cost (C)</p> Signup and view all the answers

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

<p>The sum of all edge costs for a path (B)</p> Signup and view all the answers

<p>Set of weights (B)</p> Signup and view all the answers

<p>The different states in the problem-solving process (C)</p> Signup and view all the answers

<p>A graph where connections can only be traveled in one direction (D)</p> Signup and view all the answers

<p>The mapping of actions to resulting states (D)</p> Signup and view all the answers

<p>Increased complexity with each additional location (D)</p> Signup and view all the answers

<p>Poker Game (D)</p> Signup and view all the answers

<p>The agent does not need to plan for future actions. (A)</p> Signup and view all the answers

<p>It enables agents to coordinate actions effectively. (C)</p> Signup and view all the answers

<p>AI encompasses both Machine Learning and Deep Learning. (D)</p> Signup and view all the answers

<p>Agents that improve their actions based on feedback over time. (D)</p> Signup and view all the answers

<p>The agent must make decisions with limited information. (A)</p> Signup and view all the answers

<p>Goal-based agents do not consider costs in achieving goals. (D)</p> Signup and view all the answers

<p>Sequential environments require the consideration of previous actions. (C)</p> Signup and view all the answers

The next environment state is entirely predictable based on the current state and the agent's action. The transition model predicts a unique successor state, eliminating uncertainty.

The next environment state is not deterministic, but rather a probability distribution over possible states. This means the outcome of an agent's action is uncertain.

The environment's state transitions are predictable, but the actions of other agents introduce uncertainty. This means the agent must be aware of and react to other agents in the environment.

The agent's experience is divided into independent episodes, each with a clear beginning and end. Each episode's outcomes don't influence later ones.

The agent's experience is a continuous sequence of observations and actions. Each action influences subsequent states, forming a chain of events.

The environment does not change while the agent is deliberating. The environment only changes when the agent takes an action.

The environment does not change while the agent is making decisions, but the agent's performance score is updated based on the passage of time.

The environment has a fixed number of distinct perceptions, actions and states. All values are distinct and quantifiable.

The field of study that focuses on creating intelligent agents that can learn, reason, and make decisions like humans.

A specific area within AI that uses data to enable computer systems to learn and improve their performance automatically. Examples include image recognition, language translation, and self-driving cars.

The process of representing knowledge in a structured way so that computers can understand and reason with it. It involves expressing information in a form that computers can interpret and manipulate.

The ability of a computer system to draw conclusions and solve problems using the knowledge it has acquired. It involves using logic and inference rules.

The ability of a computer system to acquire new knowledge and skills from experiences or data without being explicitly programmed. This involves techniques like supervised, unsupervised, and reinforcement learning.

A specific type of AI that focuses on training computers to perform tasks by learning from data and examples. Common examples include image classification, object detection, and natural language processing.

A type of AI that aims to find patterns and structure in unlabeled data. This is useful for tasks like grouping similar objects, discovering anomalies, and identifying hidden relationships in data.

An AI technique where an agent learns by interacting with its environment and receiving rewards or penalties for its actions. It involves finding optimal strategies to maximize rewards.

A list containing the nodes that have been visited and are currently on the path being explored.

A task environment where the agent can fully perceive the state of the environment at any given time.

A list containing the nodes that are next to be visited.

A task environment where the agent's perception of the environment is incomplete or limited.

A list containing the nodes that have been explored and found to be dead ends.

The node currently being explored.

A system where multiple agents interact with each other and the environment, often with shared goals or competing interests.

The algorithm explores all possible paths until it finds a solution or exhausts all possibilities.

An agent learns and adapts its behavior through experience or feedback. The agent's performance improves over time.

The practice of extracting meaningful insights and patterns from large and complex data sets.

A branch of computer science concerned with the design and development of intelligent agents that can interact with the environment and achieve goals.

The desired end state in a problem-solving process. It specifies the conditions that need to be met for a solution to be considered successful.

A sequence of actions that leads from the initial state to the goal state. It represents the path taken to solve a problem.

The cost associated with following a specific solution path. It is typically a sum of the costs of individual actions taken.

The set of all possible states reachable from the initial state by taking any sequence of actions. It encompasses the entire problem space.

A graph that represents the state space of a problem. It consists of nodes representing states and links representing actions between states.

A mathematical structure used to represent relationships between objects. It consists of nodes and links connecting them.

A representation of the state space using a four-tuple [N, A, S, GD] where N is the set of states, A is the set of actions, S is the initial state, and GD is the goal state.

A simple example of a problem that demonstrates the concepts of state space, actions, and goal state. Involves an agent cleaning up dirt in a world with multiple locations.

A computer program that can perceive its environment, reason about its actions, and act autonomously or collaboratively to achieve specific goals.

A way to describe computer systems that mimic human intelligence, focusing on rational or logical actions rather than trying to exactly replicate how humans think.

A way to describe computer systems that imitate human behavior, considering not only logical decisions but also the emotional and cognitive aspects of thought.

A systematic search through a set of possible solutions, considering each step and its consequences to find the best path to solve a problem.

A system that uses knowledge extracted from human experts to solve problems by building a model that can be applied to similar situations.

Inspired by the human brain's structure, these models use interconnected nodes to process information. They are used to build intelligent programs.

These algorithms use concepts of evolution to create new solutions for problems by combining and modifying existing solutions.