Home
Subjects
Explanations
Create
Study sets, textbooks, questions
Log in
Sign up
Upgrade to remove ads
Only $2.99/month
Science
Computer Science
Artificial Intelligence
3.2 Discovering Knowledge from Data
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Terms in this set (19)
Abstraction in Models
Abstraction is generalization with loss of detail. A model abstracts many details, often by reducing several factors into a single parameter. The use of a single number for the reflectivity of clouds in a climate model is an abstraction.
Comma Separated Value File (CSV)
The most widely readable form of data. A file format in which each line contains multiple values separated by a comma. There are many CSV standards. Most of them allow string values which can contain commas inside a quote.
Confidence Interval
A range of values given as a prediction. The range is chosen so that statistically such predictions will be correct a certain percentage of the time, typically 95% of the time.
Disaggregating Data
When disaggregating data, you separate the data based on one variable in order to compare values of another variable between groups.
Edge or Link
Connection between two nodes in a graph.
Graph
A network of nodes connected by links.
Inferential Statistics
Makes predictions about a population of measurements based on a sample of measurements.
Latitude
Position on the Earth north-to-south, measured in degrees from -90 (south pole) to +90 (north pole).
Longitude
Position on the Earth East/West measured in degrees from -180 to +180, with 0 passing through England.
Model
Mathematical constants, relationships, and algorithms used to describe something real. A model includes some patterns of the real thing and abstracts away other details.
Monte Carlo Simulation
Using a random number generator to observe the range of results that occur in a simulation that has random variability.
Narrow AI
Artificial intelligence in which a program is written to accomplish a specific task.
Node
A point in a graph, the kind of graph that describes a network.
Parameter
A value used in a model.
p-value
The p-value, or just p, is the probability that an apparent pattern (such as the value of variable being associated with the value of another variable) has arisen by chance and not due to a pattern that actually exists. Typically p<0.05 is accepted as scientific evidence.
Simulation
Use of a model to generate meaningful but fictional data.
Strong AI
Artificial intelligence with a generalized learning ability, on par with human intelligence.
Training Set
A data set in which the input and the desired output are both provided to the computer.
Validation Set
A data set in which the input is provided to the computer and the desired output is known, so that it can be determined how well a machine learning an algorithm is working.
Recommended textbook explanations
C++ For Everyone
2nd Edition
Horstman
359 explanations
C++ for Everyone
2nd Edition
Cay S. Horstmann
359 explanations
Java Methods: Object-Oriented Programming and Data Structures
3rd Edition
Gary Litvin, Maria Litvin
285 explanations
C++ How to Program (Early Objects Version)
9th Edition
Harvey M. Deitel, Paul J. Deitel
523 explanations
Sets with similar terms
3.2 Key Terms
19 terms
Cis 4640: Exam # 1 Review
36 terms
BSAD 315 Ch. 1
31 terms
Ch. 9 Big Data Analytics for Managing Risk
45 terms
Other sets by this creator
Unit 5 - Applications of Integration
7 terms
Unit 4 - Integration
16 terms
MTH107 Unit 1 - Sampling and Data
42 terms
Unit 3 - Applications of Differentiation
30 terms