Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 9

MACHINE

LEARNING
WHAT IS MACHINE
LEARNING?
Is a subfield of
Is used today for a
AI refers to the
Artificial Intelligence (AI)
wide range of commercial
general attempts to create
that uses algorithms
purposes, including
machines capable of
trained on a data sets to suggesting products to
human-like cognitive
create self-learning consumers based on their
abilities, machine learning
models that are capable past purchases, predicting
specifically refers to the
of predicting outcomes stock market fluctuation,
use of algorithms and
and classifying and translating text from
data sets to do so.
information without one language to another.
human intervention.
EXAMPLE OF MACHINE LEARNING
Virtual Assistants Email Filtering

Recommendation
System

Social Media
Fraud Detection
Feed
Personalization
MACHINE LEARNING
VS
DEEP LEARNING
Machine Learning refers to Deep Learning, meanwhile, is a subset
of machine learning that layers
the general use of algorithms
algorithms into “neural networks” that
and data to create somewhat resemble the human brain
autonomous or semi- so that machine can perform complex

autonomous machine. task.


TYPES OF
MACHINE
LEARNING
Several different types  Supervised Machine Learning
of machine learning power that
many different digital goods and  Unsupervised Machine Learning
services we use everyday.
Here’s an overview of the
 Semi-supervised Machine Learning
different types of machine
learning primarily in use today.
SUPERVISED MACHINE
LEARNING
In Supervised Machine Learning, algorithms are labeled data sets that
include tags describing each piece of data. In other words, the algorithms are
fed data that include an “answer key” describing how the data should be
interpreted.

Supervised Machine Learning has a wide range of applications,


including image and speech recognition, natural language processing, fraud
detection, and recommendation systems.
UNSUPERVISED MACHINE
LEARNING
Unsupervised Machine Learning is a type of machine learning where
the algorithms learns from unlabeled data without any specific output labels.
The goal is to find patterns, relationships, or structures within the data
without prior knowledge of what the output should be.

Unsupervised learning has a wide range of applications, including


customer segmentation, market basket analysis, image and text clustering,
and anomaly detection in cybersecurity.
SEMI-SUPERVISED MACHINE
LEARNING
Semi-supervised Machine Learning is a combination of supervised
and unsupervised learning techniques. It is used when we have a small
amount of labeled data and a large amount of unlabeled data.

Semi-supervised learning can be beneficial in scenarios where


obtaining labeled data is challenging or costly, but there is a large amount of
unlabeled data available. It can be applied in various domains, such as text
classification, image recognition, and fraud detection.

You might also like