What is Artificial Intelligence (AI)?
Artificial Intelligence (AI) refers to the process of creating machine intelligence
by using either software or hardware to enable machines to perform various types of
work and tasks that humans would typic
ally complete using methods or capabilities associated with human intelligence
(e.g. reasoning/learning, problem solving, understanding language and perception).
Generally, AI can be used for any of the examples noted above; for instance, some
examples of "tasks" performed by AI are:
1) Image recognition and face recognition (i.e. being able to recognize an
individual's face from a photograph).
2) Translating one language into another.
3) Playing chess or video games.
4) Driving a car.
5) Responding to questions in human language.
The ultimate objective of AI is to create intelligent, adaptive computers that can
learn and improve themselves based on the incoming data they process and complete
without a set of predefined rules.
What is Machine Learning (ML) and Deep Learning (DL)?
Machine Learning (ML) is a branch of AI; therefore, as the name implies, ML is the
capability to perform actions by having the computer system create predictive
models based on incoming data instead of having a human program them to perform
actions based on some predetermined set of programming rules.
For example, in ML, predictive models can be created by taking particular variables
in a training data set and using them to make predictions about future data.
ML has three primary types:
1) Supervised Learning – where the computer system is trained on "labeled" data
(e.g. "cat" or "dog" for a picture in the training data set).
2) Unsupervised Learning – where the computer system is trained on "unlabeled" data
(i.e. data without any pre-defined categories) (e.g. grouping customers based on
their buying patterns).
3) Reinforcement Learning, a method where a computer system learns by interacting
with its environment through trial and error, gives rewards for good actions and
penalties for bad ones, like in AI game-playing systems.
Deep Learning (DL), a part of ML, uses neural networks with many layers to find
patterns in data.
DL is often used in image and speech recognition, which requires processing large
amounts of data.
Artificial Intelligence (AI) refers to the process of creating machine intelligence
by using either software or hardware to enable machines to perform various types of
work and tasks that humans would typic
ally complete using methods or capabilities associated with human intelligence
(e.g. reasoning/learning, problem solving, understanding language and perception).
Generally, AI can be used for any of the examples noted above; for instance, some
examples of "tasks" performed by AI are:
1) Image recognition and face recognition (i.e. being able to recognize an
individual's face from a photograph).
2) Translating one language into another.
3) Playing chess or video games.
4) Driving a car.
5) Responding to questions in human language.
The ultimate objective of AI is to create intelligent, adaptive computers that can
learn and improve themselves based on the incoming data they process and complete
without a set of predefined rules.
What is Machine Learning (ML) and Deep Learning (DL)?
Machine Learning (ML) is a branch of AI; therefore, as the name implies, ML is the
capability to perform actions by having the computer system create predictive
models based on incoming data instead of having a human program them to perform
actions based on some predetermined set of programming rules.
For example, in ML, predictive models can be created by taking particular variables
in a training data set and using them to make predictions about future data.
ML has three primary types:
1) Supervised Learning – where the computer system is trained on "labeled" data
(e.g. "cat" or "dog" for a picture in the training data set).
2) Unsupervised Learning – where the computer system is trained on "unlabeled" data
(i.e. data without any pre-defined categories) (e.g. grouping customers based on
their buying patterns).
3) Reinforcement Learning, a method where a computer system learns by interacting
with its environment through trial and error, gives rewards for good actions and
penalties for bad ones, like in AI game-playing systems.
Deep Learning (DL), a part of ML, uses neural networks with many layers to find
patterns in data.
DL is often used in image and speech recognition, which requires processing large
amounts of data.
