You are on page 1of 24

HOW AI WORKS

By,
A.Shreenithi
Artificial Intelligence

Artificial intelligence works by combining large amounts


of data with fast , iterative processing and intelligent
algorithms , allowing the software to learn automatically
from patterns or features in the data.
Steps on how AI works
1. Data collection
2. Data preparation
3. Model training
4. Model testing
5. Model deployment
AI classified into two categories:
• Narrow AI:
It is a type of AI that is designed to perform a specific task ,
such as playing chess or go.
• General AI:
It is type oh AI that is designed to have the same level of
intelligence as a human being.
MACHINE LEARNING
• Machine learning (ML) is a type of artificial intelligence (AI)
that allows software applications to become more accurate in
predicting outcomes without being explicitly programmed to do
so.
• Machine learning algorithms use historical data as input to
predict new output values.
Supervised learning
• This is the most common type of machine learning. In
supervised learning, the algorithm is trained on labeled data.
• This means that the data has been tagged with the correct
output for each input.
• The algorithm learns to map the input to the output by
minimizing the error between its predictions and the actual
outputs.
Supervised learning
Image recognition:

• This is the ability to identify objects in images.


• Machine learning is used in image recognition to classify images
into different categories, such as cars, animals, or faces.
 Natural language processing (NLP):

This is the ability to understand human language.

Machine learning is used in NLP to tasks such as


machine translation, text summarization, and
question answering.
 Speech recognition:
This is the ability to convert speech into text.
Machine learning is used in speech recognition to
identify the words that are being spoken.
 Fraud detection:
This is the ability to identify fraudulent transactions.

Machine learning is used in fraud detection to


identify patterns that are associated with fraudulent
transactions.
 Medical diagnosis:

This is the ability to diagnose diseases.


Machine learning is used in medical diagnosis to
identify patterns that are associated with different
diseases.
Unsupervised learning
• In unsupervised learning, the algorithm is trained on
unlabeled data.
• This means that the data does not have any tags or
labels.
• The algorithm learns to find patterns in the data
without any guidance.
Unsupervised learning
Clustering:

• This is the ability to group data points together based on their


similarities.
• Machine learning is used in clustering to identify different
groups of customers, products, or genes.
 Dimensionality reduction:
This is the ability to reduce the number of features in
a dataset while preserving the most important
information.

Machine learning is used in dimensionality reduction


to make data sets more manageable and easier to
analyze.
 Anomaly detection:
This is the ability to identify data points that are
significantly different from the rest of the data.

Machine learning is used in anomaly detection to


identify fraudulent transactions, intrusions, and
other unusual events.
Semi-supervised learning
• This is a type of machine learning that combines supervised
and unsupervised learning.
• In semi-supervised learning, the algorithm is trained on a
mixture of labeled and unlabeled data.
• The labeled data helps the algorithm to learn the patterns in
the data, while the unlabeled data helps the algorithm to
generalize its predictions to new data.
Semi-supervised learning
Image segmentation:

• This is the ability to identify different objects in an image.


• Machine learning is used in image segmentation to
identify the different parts of an image, such as the sky,
the ground, and the objects in the foreground.
 Text classification:

This is the ability to classify text into different


categories, such as news articles, product
reviews, and social media posts.

Machine learning is used in text classification to


identify the different types of text in a corpus.
 Recommendation systems:

This is the ability to recommend products or


services to users based on their past behavior.

Machine learning is used in recommendation


systems to identify products or services that users
are likely to be interested in.
Reinforcement learning
• In reinforcement learning, the algorithm learns by trial and
error.
• The algorithm is rewarded for taking actions that lead to
desired outcomes and punished for taking actions that lead to
undesired outcomes.
• The algorithm learns to take actions that maximize its rewards.
Reinforcement learning
Robotics:

• This is the ability to control robots to perform tasks in the real


world.
• Machine learning is used in robotics to train robots to learn
how to perform tasks such as walking, picking up objects, and
navigating through obstacles.
 Game playing:
This is the ability to play games against humans or
other machines.

Machine learning is used in game playing to train


agents to learn how to play games such as chess, Go,
and Dota 2.
 Financial trading:
This is the ability to make trading decisions based on
market data.

Machine learning is used in financial trading to train


agents to learn how to make profitable trading
decisions.
THANK YOU
C

You might also like