AI BASICS
Teaching computers and machines to think, reason, and
learn from information.
Artificial Intelligence (AI)
The AI pillar that uses eyes, ears, or other inputs to
notice things.
Perception
Simple signals collected by sensors before a computer
has assigned meaning to them.
Raw Data
The special way an AI makes decisions by following
rules.
Reasoning
In an algorithm, the 'ingredients' or information the task
needs.
Input
Information given to computers so they can learn, think,
and make decisions.
Data
The AI pillar involving thinking and making a plan to
solve a problem.
Reasoning
A device that captures light and color information for a
computer.
Camera
The basic logic pattern: IF an attribute matches a rule,
THEN the computer takes an action.
If-Then Rule
In an algorithm, the finished result or solved problem.
Output
A special list of step-by-step instructions a computer
follows to complete a task.
Algorithm
The AI pillar involving getting better at something by
practicing with information.
Learning
A device that records sound as vibration information.
Microphone
A place where AI asks a specific question to decide what
to do next.
Decision Node
The step where an AI looks for similarities in
information.
Patterns
The way a computer gets better at something by
practicing with information.
Machine Learning
The AI pillar involving talking, listening, and working
together with people.
Interaction
The process of turning real-world objects into tags that
computers can understand.
Data Representation
A diagram where one question leads to another until an
answer is found.
Decision Tree
The three-part AI process: Input, Process, and this step.
Learn
Specific information used to teach an AI model how to
find patterns and make predictions.
Training Data
The AI pillar focused on how AI helps or changes the way
we live.
Societal Impact
Descriptions such as color, shape, and texture that tell a
computer about an object.
Tags / Attributes
In a fruit-sorting example, the question 'Texture =
Smooth?' is this part of the decision process.
Decision Node
The lecture's analogy says the algorithm is the map,
data is the fuel, and machine learning is this.
Machine Learning