Scribd
Upload
5 views10 pages

Machine Learning Basics and Applications

The document provides an overview of Machine Learning (ML) as a subset of AI, detailing its processes, types of problems it can solve (regression, classification, clustering), and the role of Deep Learning and Neural Networks. It explains the components of neural networks, including weights, biases, and activation functions, as well as practical applications of AI technologies like voice assistants and e-commerce recommendations. The document concludes with an invitation for an interactive workshop and Q&A session.

Uploaded by

suresh
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
5 views10 pages

Machine Learning Basics and Applications

The document provides an overview of Machine Learning (ML) as a subset of AI, detailing its processes, types of problems it can solve (regression, classification, clustering), and the role of Deep Learning and Neural Networks. It explains the components of neural networks, including weights, biases, and activation functions, as well as practical applications of AI technologies like voice assistants and e-commerce recommendations. The document concludes with an invitation for an interactive workshop and Q&A session.

Uploaded by

suresh
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

Module - 2

AI Technologies
Machine Learning: Basics and
Beyond
• Definition: "Machine Learning is a subset of AI where systems learn patterns from
data to make decisions without explicit programming."

• A Machine Learning process begins by feeding the machine lots of data.


• The machine is then trained on this data, to detect hidden insights and patterns.
• These insights are used to build a Machine Learning Model by using an algorithm
in order to solve a problem.
Types of
Machinelearning
What Problems Can Machine Learning Solve?

1 2 3
Regression Classification Clustering
In this type of problem, In this type, the output is a This type of problem
the output is a continuous categorical value. involves assigning the
quantity. Classifying emails into two input into two or more
For example, if you want classes, spam and non- clusters based on feature
to predict the speed of a spam is a classification similarity.
car given the distance, it problem that can be For example, clustering
is a Regression problem. solved by using Supervised viewers into similar
Regression problems can Learning classification groups based on their
be solved by using algorithms such as Support interests, age, geography,
Supervised Learning Vector Machines, Naive etc can be done by using
algorithms like Linear Bayes, Logistic Regression, Unsupervised Learning
Regression. K Nearest Neighbor, etc. algorithms like K-Means
Clustering.
Deep Learning and Neural Networks
• Definition: "Deep Learning is a subset of ML inspired by the structure and
function of the human brain, using neural networks to analyze data."

• How Neural Networks Work:


• Input Layer: Takes in raw data (e.g., images, text).
• Hidden Layers: Process data through interconnected nodes (neurons).
• Output Layer: Produces predictions or classifications.
Weights and Bias
• Once an input variable is fed to the network, a
randomly chosen value is assigned as the weight of
that input. The weight of each input data point
indicates how important that input is in predicting
the outcome.
• The bias parameter, on the other hand, allows you
to adjust the activation function curve in such a way
that a precise output is achieved.
Summation Function
• Once the inputs are assigned some weight, the
product of the respective input and weight is taken.
Adding all these products gives us the Weighted
Sum. This is done by the summation function.
Activation Function
• The main aim of the activation functions is to map
the weighted sum to the output. Activation
functions such as tanh, ReLU, sigmoid and so on are
examples of transformation functions.
AI Technologies in Action

Voice Assistants (e.g., E-Commerce


Autonomous Vehicles:
Siri, Alexa) Recommendations:

Uses natural language processing to Combines ML, computer vision, and Analyzes user behavior to suggest
understand and respond to queries. sensors to navigate safely. products, increasing sales and user
satisfaction.
Interactive Workshop
Lets begin..... !
Q&A

You might also like