Scribd
Upload
7 views11 pages

Unidad 2

The document discusses the critical role of data in artificial intelligence (AI) and its various components, including data science, data engineering, data mining, and machine learning. It outlines different machine learning approaches such as supervised, unsupervised, and reinforcement learning, as well as deep learning techniques that mimic human cognitive processes. The authors emphasize the importance of data quality and ethical considerations in leveraging AI for decision-making and personalized solutions.

Uploaded by

navaisabela864
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views11 pages

Unidad 2

The document discusses the critical role of data in artificial intelligence (AI) and its various components, including data science, data engineering, data mining, and machine learning. It outlines different machine learning approaches such as supervised, unsupervised, and reinforcement learning, as well as deep learning techniques that mimic human cognitive processes. The authors emphasize the importance of data quality and ethical considerations in leveraging AI for decision-making and personalized solutions.

Uploaded by

navaisabela864
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Inteligencia

Artificial
BASADA EN DATOS
Introduction
Data is the lifeblood of AI. The more data these
algorithms consume, the more proficient
they become at understanding, predicting and
delivering personalized solutions. But
beneath this promise lies a complex world of
challenges, from ethical concerns to data
quality and privacy issues.
Data science
fundamentals
Data science combines mathematics and
statistics, specialized programming,
advanced
analytics, artificial intelligence (AI) and
machine learning with subject-specific
knowledge
to uncover actionable insights hidden in
an organization's data. These insights can
be used
to guide decision making and strategic
planning
Data
engineering.
Data engineering is a key discipline
in the field of data science, as it is
responsible for
designing, building, and maintaining
the infrastructure and tools needed
to collect, store, and process data.
This includes tasks such as data
warehousing, data integration and
data
quality management.
Data mining
Data mining is the use of machine learning and statistical analysis to discover patterns and
other valuable information from large data sets.
Data mining techniques that underpin data analytics can be deployed for two main
purposes. They can describe the target dataset or predict results using machine learning
algorithms.
Machine learning

Machine learning (ML) is the subsection of artificial intelligence (AI) that focuses on
developing systems that learn, or improve performance, based on the data they consume.
Artificial intelligence is a broad term that refers to systems or machines that mimic human
intelligence. Machine learning and AI are often named together, and the terms are
sometimes used interchangeably, but they do not mean the same thing. An important point
to note is that while all machine learning is AI, not all AI is machine learning.
Supervised learning

Supervised machine learning algorithms are the most commonly used. With this model, a
data scientist acts as a guide and teaches the algorithm what conclusions to draw. Like a
child learning to identify fruits by memorizing them with a picture book, in supervised
learning, the algorithm is trained by a data set that is already labeled and has a
predefined
outcome.
Examples of supervised machine learning include algorithms such as linear and logistic
regression, multiclass classification, and support vector machines
Unsupervised learning
Unsupervised machine learning uses a more independent approach, in which a
computer
learns to identify complex processes and patterns without close and constant
guidance from
a human being. Unsupervised machine learning involves training based on data that has
neither labels nor a specific defined outcome.
Examples of unsupervised machine learning algorithms include k-means clustering,
principal and independent component analysis, and association laws
Reinforcement Learning

Reinforcement learning (RL) is a machine learning (ML) technique that


trains software to
make decisions and achieve the best results. It mimics the trial-and-
error learning process
that humans use to achieve their goals. Software actions that work
towards their goal are
reinforced, while those that deviate from the goal are ignored.
RL algorithms use a reward and punishment paradigm when
processing data. They learn
from the feedback of each action and discover for themselves the
best processing paths to
achieve the final results.
Deep learning
Deep learning is a method of artificial intelligence (AI) that trains computers to
process
data in a way that is inspired by the human brain. Deep learning models are able to
recognize complex patterns in images, text, sounds and other data in order to
generate
accurate information and predictions. Deep learning methods can be used to automate
tasks
that usually require human intelligence, such as describing images or transcribing a
sound
file into text.
Gracias por
su atención
Melissa Paloma Sanchez Hernández
Isabella Pérez nava
Anthony Dylan zainos Pérez

You might also like