AI Final Keywords

0.0(0)
studied byStudied by 0 people
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
Card Sorting

1/57

encourage image

There's no tags or description

Looks like no tags are added yet.

Study Analytics
Name
Mastery
Learn
Test
Matching
Spaced

No study sessions yet.

58 Terms

1
New cards

Population

A group of candidate solutions to the problem.

2
New cards

Chromosome

A representation of a candidate solution, often as a string or array.

3
New cards

Fitness Function

A function used to evaluate the quality or "fitness" of a candidate solution. Is a particular type of objective function that is used to summarise, as a single figure of merit, how close a given design solution is to achieving the set aims. It is used in genetic programming and genetic algorithms to guide simulations towards optimal design solutions.

4
New cards

Selection

The process of choosing parent solutions based on their fitness to pass traits to the next generation.

5
New cards

Crossover

A genetic operator that combines two parent solutions to create offspring solutions.

6
New cards

Mutation

A genetic operator that introduces random changes in offspring to maintain diversity and avoid local optima.

7
New cards

Generation

One iteration of the algorithm, including selection, crossover, and mutation steps.

8
New cards

Optimization

The process of finding the best solution or set of solutions.

9
New cards

Convergence

When the algorithm stabilizes, and no further improvement is observed in the fitness of the population.

10
New cards

Search Space

The domain of all possible solutions to the problem.

11
New cards

Elitism

Preserving the best individuals in the population to ensure their traits are carried forward.

12
New cards

Agent

A system with at least some form of intelligence considering the main 6 factors.

13
New cards

Agent Function

What an agent is supposed to do, its purpose.

14
New cards

Agent Program

An internal absolute implementation of code.

15
New cards

Rationality

What the agent knows about the environment and a self-judgement on how it performed.

16
New cards

Autonomy

The ability to act on its own and knowing what it has to do.

17
New cards

Reflex Agent

Responding to percepts in the environment in the right way, based on its knowledge.

18
New cards

Model Based Agent

An agent that has knowledge of the workings of the world.

19
New cards

Goal Based Agent

An agent that has knowledge of the goal and decides what actions to take to reach it.

20
New cards

Utility Based Agent

An agent that determines the best way to reach a goal.

21
New cards

Learning Agent

An agent that analyzes information to make improvements.

22
New cards

Algorithms

A set of rules or instructions given to an AI, neural network, or other machines to help it learn on its own; classification, clustering, recommendation, and regression are four of the most popular types.

23
New cards

Artificial Intelligence

A machine’s ability to make decisions and perform tasks that simulate human intelligence and behavior.

24
New cards

Artificial Neural Network (ANN)

A learning model created to act like a human brain that solves tasks that are too difficult for traditional computer systems to solve.

25
New cards

Autonomic Computing

A system's capacity for adaptive self-management of its own resources for high-level computing functions without user input.

26
New cards

Chatbots

A chat robot (chatbot for short) that is designed to simulate a conversation with human users by communicating through text chats, voice commands, or both. They are a commonly used interface for computer programs that include AI capabilities.

27
New cards

Classification

Classification algorithms let machines assign a category to a data point based on training data.

28
New cards

Cluster Analysis

A type of unsupervised learning used for exploratory data analysis to find hidden patterns or grouping in data; clusters are modelled with a measure of similarity defined by metrics such as Euclidean or probabilistic distance.

29
New cards

Clustering

Algorithms that group data points into groups with similar characteristics.

30
New cards

Cognitive Computing

A computerized model that mimics the way the human brain thinks. It involves self-learning through the use of data mining, natural language processing, and pattern recognition.

31
New cards

Convolutional Neural Network (CNN)

A type of neural network that identifies and makes sense of images.

32
New cards

Data Mining

The examination of data sets to discover patterns that can be useful.

33
New cards

Data Science

An interdisciplinary field that combines scientific methods, systems, and processes from statistics, information science, and computer science to provide insight into phenomenon via either structured or unstructured data.

34
New cards

Decision Tree

A tree and branch-based model used to map decisions and their possible consequences, similar to a flow chart.

35
New cards

Deep Learning

The ability for machines to autonomously mimic human thought patterns through artificial neural networks composed of cascading layers of information.

36
New cards

Game AI

A form of AI specific to gaming that uses an algorithm to replace randomness. It is a computational behavior used in non-player characters to generate human-like intelligence and reaction-based actions taken by the player.

37
New cards

Genetic Algorithm

It is usually considered as Unsupervised learning algorithm. It is a search heuristic that is inspired by Charles Darwin’s theory of natural evolution. This algorithm reflects the process of natural selection where the fittest individuals are selected for reproduction in order to produce offspring of the next generation.

38
New cards

Heuristic Search Techniques

Support that narrows down the search for optimal solutions for a problem by eliminating options that are incorrect.

39
New cards

Knowledge Engineering

The focus on building knowledge-based systems, including all of the scientific, technical, and social aspects of it.

40
New cards

Logic Programming

A type of programming paradigm in which computation is carried out based on the knowledge repository of facts and rules; LISP and Prolog are two logic programming languages used for AI programming.

41
New cards

Machine Intelligence

An umbrella term that encompasses machine learning, deep learning, and classical learning algorithms.

42
New cards

Machine Perception

The ability for a system to receive and interpret data from the outside world similarly to how humans use our senses. This is typically done with attached hardware, though software is also usable.

43
New cards

Natural Language Processing

The ability for a program to understand human language.

44
New cards

Recurrent Neural Network (RNN)

A type of neural network that makes sense of sequential information and recognize patterns, and creates outputs based on those calculations.

45
New cards

Supervised Learning

A type of machine learning in which output datasets train the machine to generate the desired algorithms, like a teacher supervising a student; more common than unsupervised learning.

46
New cards

Swarm Behavior

From the perspective of the mathematical modeler, it is an emergent behavior arising from simple rules that are followed by individuals and does not involve any central coordination.

47
New cards

Unsupervised Learning

A type of machine learning algorithm used to draw inferences from datasets consisting of input data without labelled responses. The most common unsupervised learning method is cluster analysis.

48
New cards

Backpropagation (BP)

An algorithm used to train ANN. It distributed the error term back up through the layers, by modifying the weights at each node. It is commonly used to train deep neural networks.

49
New cards

NLP

Gives machines the ability to read and understand human language.

50
New cards

Machine Learning

Is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

51
New cards

Deep Learning

In this advanced version of machine learning, computers actually teach themselves with minimal programming by humans. Marketers can use deep learning to identify data and make predictions related to how consumers might behave.

52
New cards

ANN

is a class of machine learning algorithms that uses multiple layers to progressively extract higher level features from the raw input. For example, in image processing, lower layers may identify edges, while higher layers may identify the concepts relevant to a human such as digits or letters or faces.

53
New cards

Swarm Intelligence

Are computing systems inspired by the biological neural networks that constitute animal brains. The neural network is a framework for many different machine learning algorithms to work together and process complex data inputs.

54
New cards

Learning Rate

The amount that the weights are updated during training.

55
New cards

Cognitive Science

The broader form of study that includes AI in addition to philosophy, linguistics, psychology, neuroscience, and anthropology. All of these combine together to learn how the mind functions and, when applied to AI, how machines can simulate human thought and action.

56
New cards

Ant Colony Algorithm

An algorithm for finding optimal paths based on ant behavior.

57
New cards

AI Programming Language

Languages like Python, R, Java, C, Java Script, C++ used for AI programming.

58
New cards

Fluent

A type of condition that can change over time.