A decision method designed to minimize potential losses and maximize potential gains for a given player
In minimax, minimizing refers to an opponent who is looking for their optimal move.
In minimax, maximizing refers to a player who is looking for their own optimal move.
An artificial intelligence model that is commonly used in games to model the behavior of a non-playable character (NPC). It consists of a set of finite states with associated transitions that occur based on certain events, which cause the character between different behaviors.
A character in a game that is controlled by an artificial intelligence (AI) agent rather than a player.
An algorithm that starts at the root of a search tree and explores its nodes to find a node that satisfies the conditions mentioned in a search problem
A technique used to find an approximate solution, rather than trying all possible search paths
A technique that will limit the minimax algorithm so that it only explores the game tree from the root node to a given depth
An optimization technique that compares the current maximum and minimum scores in the game and stops minimax from executing if the minimum score is lower than the maximum
The best (highest) maximum score
The best (lowest) minimum score
At a high level, recursion is when a function (or method) calls itself.
The base case is the simplest form of the recursive problem. The base case can be immediately solved without breaking the problem down any further.
The recursive case is the general form of the recursive problem. In this case the problem needs to be broken down by one step toward the base case, and the algorithm makes a recursive call to itself to solve this slightly smaller problem. This process repeats until the base case is reached.
Infinite recursion occurs when the base case can never be reached.
Machine learning is a field of Artificial Intelligence that uses inputs and outputs to create computer models that teaches a computer to have intelligence.
A form of machine learning where algorithms are trained to make predictions using testing data, where the outcome of a specific event is already determined
A machine learning model that attempts to create a linear relationship between the inputs in an algorithm to the expected output
The variables or data points that shape and impact the outcome of a model, that are represented on the x-axis
The variables or data points, that are represented on the y-axis, that directly depends on the independent variable
The line, or linear equation that best expresses the relationships between all data points. A line is considered to be the best fit if it has the smallest total distance from each data point.
A statistical formula that is able to determine the total distance between all data points and their respective place on the predicted line
A function that measures the performance of a Machine Learning model for given data. An example of a cost function is the least square method.
The slope of the linear model, which determines how steep the line is, or how much a dependent variable changes compared to the independent variable
The intercept where the line of best fit intercepts the y-axis
Data points that stray away from the given pattern can impact the line of best fit, causing the accuracy of the model to decrease
The strength of the relationship between numeric values. It determines whether or not independent and dependent variables have a relationship to one another.
As one variable changes, 100% of the time the other will change the exact same amount
As one variable increases, the other variable increases.
As one variable increases, the other variable decreases.
A statistical equation that seeks to determine the variability of a variable, or how standard its change is, compared to the product of their standard deviations.
A machine learning model for predicting the value of one dependent variable based on two or more independent variables
A machine learning library that provides public access to machine learning algorithms
A value that indicates how well the model fits the data, where 1 is a model that perfectly fits the data and 0 represents a model that doesn’t fit the data at all.
The process of normalizing the range between different variables in a dataset
The result of standardization is the features will be rescaled to ensure the mean and the standard deviation to be 0 and 1
A supervised learning classification algorithm used to predict the probability of a target variable
A predictive modeling problem where a label is predicted for a given input
A common unsupervised learning technique that takes a data set and divides it into subgroups, or clusters, based on similarities
A type of clustering that determines the similarity of data points based on their closeness to the centroid, or center, of a cluster
An iterative clustering algorithm that uses an expectation-maximization approach to separate the data into clusters
An iterative process that calculates the impact that different K values have on the structure of the dataset
The step where the algorithm randomly assigns each data point to a cluster
The step where the algorithm calculates the centroids by finding the center between all of its cluster data points
A data point at the center of a cluster
A large percent of a dataset that is used to teach a machine learning model
A smaller subset of a dataset that is used test a trained machine learning model
An algorithm is a set of steps or rules to follow to solve a particular problem.
A computer system able to perform tasks that ordinarily require human intelligence
The ability to perceive and interpret information, and to retain it as knowledge to be applied in the correct context
A machine that is able to apply intelligence to any problem and could act and behave like humans
An algorithm that takes voice input and translates it into text
A machine that is able to apply intelligence to a single problem
The moral principle that governs a person's behavior.
The systematic and repeatable errors in a computer system that create unfair outcomes
A form of machine learning where algorithms are able to group data and find patterns in the data on their own
A type of machine learning that uses a computational model that uses nodes inspired by the structure and functioning of the human brain and learns by trial and error.
A weight given to a data point to determine how “important” a specific input is in relation to a given output
Chatbots that are able to analyze user text and respond to users based on a set of established responses
A test that determines how realistic, or humanlike a computer system really is. If a human is unable to tell if it is talking to a computer or a human, then the computer is said to have passed the Turing test.
A program designed to simulate a human conversation
A chatbot that provides users with a series of limited options that they can choose from to get more information from the chatbot. Rather than support a true conversation, rule-based chatbots tend to provide information and services that follow strict rules.
A visual support tool that helps document the possible conditional statements that could be executed in a given algorithm
A function that prints a prompt and retrieves text from the user.
Python method that returns a copy of the string you call it on, without any whitespace at the beginning or end.
A general term in programming that refers to the flow of information into and out of a program
A function that reads in a file into a program
A character used to represent the end of a line of text and the beginning of a new line
A Python method that returns a list of strings after breaking the given string by the specified separator
A Python library that uses machine learning to respond to user input and create dialogue. Chatterbot chatbots start out as untrained and improve their conversational ability after every conversation and user input.
A Chatterbot module that can be used to train a chatbot to respond to conversations
A Chatterbot method that takes user input as a parameter, and returns a chatbot string response
