chapter 1 Flashcards
_____ refers to the simulation of human intelligence by intelligent agents, either physical or software, that is taught to think and behave like people.
Artificial intelligence (AI)
Artificial intelligence is a broad field in which computers to solve problems by simulating complex biological processes such as
learning, reasoning, and self-correction.
It is the subfield of AI that is employed in a variety of applications such as learning current events, formulating solutions for existing problems and recommend for future events, and classifying similar ones to make day-to-day life easier.
Machine learning
machine learning can be either ___ or ____
predictive or descriptive
A technology that is used to train machines to perform various actions such as predictions, recommendations and estimations, etc., based on
historical data or past experience.
A technique which enables a machine to mimic human behaviors
AI
uses statistical methods to enable machine to improve with experiences
ML
which computers learn from experience and comprehend the world through the use of concept hierarchy. It advances to solve problems involving unstructured data sets such as images, video, and free text.
Deep learning
ML working procedure
- data acquisition and understanding
- data cleaning
- modeling
- deployment
Types of Machine learning: Based on input data
supervised, unsupervised and reinforcement
an algorithm to accurately assign test data into specific categories. It recognizes specific entities within the dataset and attempts to draw some conclusions on how those entities should be labeled or defined
classification
ML classification
binary, multi-class and multi label classification
an algorithms predict the output values based on input features from the data fed in the system.
Regression
Unsupervised learning models are utilized for three main tasks—
clustering, association, and dimensionality reduction.
list four Characteristics of Reinforcement Learning
no supervisor, sequential decision making and time play crucial rule