Artificial Intelligence Vocabulary Flashcards

Introduction to Artificial Intelligence

Artificial Intelligence (AI) is a field dedicated to the development of systems that simulate human activities like perceiving, reasoning, learning, and acting. AI leverages various technologies to create systems that can act in ways reminiscent of human intelligence.

Scope and Areas of AI

AI encompasses several subfields, each focusing on different methods and applications:

• Machine Learning: Involves algorithms that enable systems to learn from data without being explicitly programmed.

• Deep Learning: A subset of machine learning involving artificial neural networks that process vast amounts of unstructured data.

• Natural Language Processing (NLP): Focuses on interactions between computers and human languages.

• Computer Vision: Deals with how computers can gain understanding from digital images or videos.

• Robotics: Encompasses designing and operating robots that can perform tasks autonomously.

Intelligent Agents

Intelligent agents can either be software or physical systems:

• Software Agents: Programs designed for tasks like email filtering or web search.

• Physical Agents (Robots): Programmable machines that can perform various jobs, including assembly and navigation.

Key Functions of Intelligent Agents

1. Acting: Agents must perform actions based on computations.

2. Sensing: They must be able to perceive their environment.

3. Reasoning: Agents must process information to make decisions.

4. Learning: Adapting their behavior based on new data or experiences.

Historical Development of AI

• 1950: Alan Turing proposed the Turing Test to measure a machine's ability to exhibit intelligent behavior.

• 1956: The Dartmouth Conference marked the beginning of AI as a field.

• 1965-1991: Various milestones including the creation of early AI programs, expert systems, and advancements in machine learning techniques.

Knowledge Representation

Knowledge representation involves structuring information so that an AI system can utilize it for reasoning, problem-solving, and decision-making. Various forms of representation include:

• Logic-Based: Using propositional and first-order logic to establish truths and relationships.

• Semantic Networks: Graphs that represent knowledge related to concepts and their interrelations.

• Frames: Data structures that hold knowledge about a particular object or concept.

Difference Between Data, Information, and Knowledge

• Data: Raw facts that can be verified.

• Information: Processed data structured meaningfully.

• Knowledge: Insights drawn from information that can guide decisions and actions.

Problem-Solving in AI

AI relies heavily on problem-solving methodologies, which typically involve covering a search space where different paths lead to potential solutions. For instance:

1. Define the problem and its initial state.

2. Determine possible actions transforming one state to another.

3. Find a goal state through a systematic exploration of the search space.

Search Techniques

There are two primary types of search techniques:

1. Uninformed Search: Also known as blind search; it explores the state space blindly without domain knowledge, e.g., Depth-First Search (DFS) and Breadth-First Search (BFS).

   • DFS: Explores as deeply as possible before backtracking.

   • BFS: Explores all neighboring nodes at the present depth prior to moving on to nodes at the next depth level.

2. Informed Search: Uses heuristics to guide the search, improving efficiency. Examples include the A* algorithm, which calculates the least cost path by evaluating current and estimated future costs.

Evaluation of Search Strategies

When assessing a search algorithm, several factors are important:

• Completeness: Whether the algorithm is guaranteed to find a solution if it exists.

• Optimality: If the solution found is the best (minimal cost).

• Time complexity: The time it takes to find a solution (dependent on the number of nodes expanded).

• Space complexity: The memory used by the algorithm.