0% found this document useful (0 votes)
2 views27 pages

Introduction to Machine Learning Basics

Machine learning is a subset of artificial intelligence that enables machines to learn from data and improve performance without explicit programming. It includes various types such as supervised, unsupervised, semi-supervised, and reinforcement learning, each with specific applications in areas like healthcare, image recognition, and recommendation systems. The document outlines the differences between machine learning and AI, as well as real-world examples and applications of each type of learning.

Uploaded by

elakkiya se
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2 views27 pages

Introduction to Machine Learning Basics

Machine learning is a subset of artificial intelligence that enables machines to learn from data and improve performance without explicit programming. It includes various types such as supervised, unsupervised, semi-supervised, and reinforcement learning, each with specific applications in areas like healthcare, image recognition, and recommendation systems. The document outlines the differences between machine learning and AI, as well as real-world examples and applications of each type of learning.

Uploaded by

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

Introduction to

Machine
Learning
What is machine learning
Machine learning is a type of
Artificial Intelligence that
allows machines to learn
from data and improve the
performance without being
explicit programming.
Why use machine
learning?
Machine learning allows the
user to feed a computer
algorithm for process the
amount of data and analyze
and make data-driven
recommendations and decision
based on only the input data.
How it works
 ML system use neural networks
and deep learning to collect
data, analyze data, identify
patterns and make predictions.
 ML process the data such
images, documents and
numbers.
How it’s difference from AI?
Artificial intelligence is a Machine Learning is a
tool that mimics human subset of AI that focuses on
processing and analytic teaching Machines how to
skills. perform specific task.
AI in every day life :  ML in every day life:
 Smart products  Speech and Image
 Map applications recognition
 Natural language  Traffic alerts
processing(NLP)  Chatbot
 Machine Learning(ML)  Google translation
 Robotics,  Self-driving cars
 Speech recognition and  Ads recommendations
translations.
Real world examples
 Facialrecognition (verify peoples)
 Voice assistants (Google assistant, Alexa,
Iphone’s Siri)
 Image recognition (objects, faces,
landmarks)
 Email filtering (filtering spam)
 Healthcare (mammograms)
 Direction apps (Google map)
 Recommendations (e-commerce websites)
Types of Machine Learning

There are four types of machine


leaning. They are :
 Supervised learning
 Semi – supervised learning
 Unsupervised learning
 Reinforcement learning
Supervised learning
 Based on supervision.
 It means that the machine using the
labelled data set, and based on the training
the machine predicts the output.
 In other word, the machine to be trained
with the input and with corresponding
output, then we can ask the machine to
predict the output using test dataset.
Categories of supervised
learning
 Classification (To solve
classification problem like yes or
no, male or female)
 Regression (To solve linear
relationship between the input and
output)
Supervised Learning Algorithms :
 K-Nearest Neighbors
 Linear Regression
 Logistic Regression
 Support Vector Machines (SVMs)
 Decision Trees and Random
Forests
 Neural networks
Applications of supervised
learning
 Image segmentation
 Medical diagnosis
 Fraud detection
 Spam detection
 Speech recognition
Unsupervised learning
 As it’s name suggests, there is no need
for supervision.
 The main aim of the unsupervised
leaning it to group or categories the
unsorted dataset according to the
similarities, patterns, difference.
 That the machines are instructed to find
the hidden pattern from the input
dataset.
Categories of
Unsupervised learning
 Clustering (Group the object
into cluster)
 Association (To find the
relationship among the
variables within a large
dataset)
Unsupervised Learning Algorithms :
Clustering : K-Means, DBSCAN,
Hierarchical Cluster Analysis (HCA)
Anomaly detection and novelty detection
: One-class SVM, Isolation Forest
Visualization and dimensionality
reduction : Principal Component Analysis
(PCA),Kernel PCA, Locally-Linear
Embedding (LLE) , t-distributed
Stochastic Neighbor Embedding (t-SNE)
Association rule learning : Apriori, Eclat
Applications of
Unsupervised learning

 Network analysis
 Recommendation systems
 Singular value decomposition
Semi - supervised learning
 It lies between the supervised and
Unsupervised learning.
 It uses the labelled and unlabelled
dataset during the training period.
 The main aim is to effectively use all the
available data.
 It is highly efficient.
Applications of Semi -
supervised learning
 Text document classification
 Medical imaging
 Natural language processing
 Spam email detection
 Web content classification
 Audio and image analysis
Reinforcement learning
Reinforcement learning works on a
feedback – based process.
The AI agent automatically explore
it’s surrounding by taking action,
learning from experience and
improve it’s performance.
There is no labelled data and the
agent learn from their experiences
Categories of
Reinforcement learning
 Positive reinforcement learning
(increasing the tendency by
adding something)
 Negative reinforcement learning
(increasing the tendency by
avoiding the negative condition)
Applications of
reinforcement learning
 Video games
 Resource management
 Robotics
 Text mining

You might also like