Scribd
Upload
4 views10 pages

Artificial Intelligence Presentation

Machine learning is a subfield of artificial intelligence that utilizes algorithms to create self-learning models for predicting outcomes and classifying information. It involves collecting and processing data, selecting appropriate models, training them, and evaluating their performance. Different types of machine learning include supervised, unsupervised, semi-supervised, and reinforcement learning, each with specific techniques and applications, along with associated benefits and dangers.

Uploaded by

awatef9870
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
4 views10 pages

Artificial Intelligence Presentation

Machine learning is a subfield of artificial intelligence that utilizes algorithms to create self-learning models for predicting outcomes and classifying information. It involves collecting and processing data, selecting appropriate models, training them, and evaluating their performance. Different types of machine learning include supervised, unsupervised, semi-supervised, and reinforcement learning, each with specific techniques and applications, along with associated benefits and dangers.

Uploaded by

awatef9870
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/ 10

MACHINE LEARNING

-Razan Talal ID:3910449


-Yasmin Saeed ID : 3820243
-Awatef zaid ID 4110215
-Roaa Hussein ID :3820005
Machine learning is a subfield of artificial
intelligence that uses algorithms trained on data
sets to create self-learning models that are
capable of predicting outcomes and classifying
information without human intervention.

MACHINE LEARNING DEFINITION


Machine learning works through several steps. First,
data related to the problem to be solved is collected.
The data is then processed to be cleaned and
prepared. The appropriate learning model is chosen

How does machine based on the nature of the problem and data. Next, the
model is trained using the training set, where the
learning work? model learns from the data and adjusts its internal
parameters. Model performance is evaluated using a
validation set. Ultimately, the model can be used to
predict outcomes or make decisions based on new
data.
There are several types of machine learning
algorithms powering many different digital goods and
services that we use every day. Each is designed to
handle different types of problems and data.

Types of
machine learning
It is a type of machine learning where an
algorithm is trained using previously
labeled data.
Supervised machine learning There are several popular supervised
learning algorithms, including:
Decision Trees, Support Vector
Machines, Artificial Neural Networks -
ANN.
Unsupervised machine learning

Unsupervised machine learning


There are several common techniques in
unsupervised machine learning, including:
Clustering,Principal Component Analysis -
PCA,Network Analysis,Density-Based Clustering
Semi-supervised machine learning

It is a type of machine learning that combines elements of supervised and


unsupervised learning. In this type of learning, the algorithm is trained using a set
of labeled data (containing the correct labels) and a set of unlabeled data.
Common examples of semi-supervised machine learning techniques include:
Label Propagation, Semi-Supervised Classification, Semi-Supervised Clustering.
It is a branch of machine learning that aims to teach
automated models how to make decisions and take
actions in a specific environment to achieve a specific
Reinforcement learning goal. Reinforcement learning is inspired by the way
organisms learn through trial, error, and
experimentation
Reinforcement learning consists of main elements:
Agent,Environment,State,Action,Policy,Strategy.
Benefit:
Decreased operational costs .
Improved operational efficiency and accuracy.
Improved insights.
Machine learning
benefits and dangers Dangers:
Job layoffs.
Lack of human element.
Ingrained biases.
THANK YOU

You might also like