You are on page 1of 15

Practical Training Seminar on

Machine Learning

Presented To: Presented By:


Ms. Nikita Jain Pooja Agarwal
Ms. Pooja Sharma (16EGJCS132)
TRAINING COMPANY’S PROFILE:
CETPA, the Composition of "Computer Education
& Technology Promotion Association", believes in
quality not in quantity because knowledge matters.
It has specialization in 3 important domains
namely training, development and consultancy.
The company provides specialized training in 50+
leading technologies like .NET, Java, PHP, Ethical
Hacking, ANDROID, CCNA, AUTOCAD, VHDL,
MATLAB, EMBEDDED SYSTEM, HVAC,ML and
many more.

Trainer: Mr. Rahul Pathak

Address: D-58, Sector-2, Near Red FM.


Noida -201301,
Uttar Pradesh
CONTENTS:

1.) Introduction to machine learning


2.) Types of analysis
3.) End to end data science project
4.) Types of machine learning algorithms
5.) Project

6.) Conclusion
WHAT IS MACHINE LEARNING?

A machine is said to have learned


from experience(E) on some
task(T) and some performance
measure(P) , if on task(T) the
performance measure(P)
increases over experience(E).

- Tom Michale(1997)
TYPES OF ANALYSIS:

Data analytics or descriptive


analysis deals with the past
while machine learning is
concerned with future.
END TO END DATA SCIENCE PROJECT

1.) Get the data


2.) Discover and visualize to gain insights
3.) Data preprocessing
4.) Select and train a machine learning algorithm
5.) Fine tuning
6.) launch monitor and maintain your system
TYPES OF MACHINE LEARNING
ALGORITHMS
SUPERVISED LEARNING

Regression: This type of algorithm


is used for predicting continuous
values such as salary .

Classification: This type of


algorithm is used for predicting
categorical values such as yes/no.
UNSUPERVISED LEARNING

K-means clustering: It is a
top to bottom approach that
uses averaging method to
create optimal clusters.
PROJECT : HEALTHCARE DOMAIN CHATBOT

A chatbot is a computer program designed to simulate conversation with


human users, especially over the Internet.

• Admin has to collect the patients medical history of records and


filter it appropriately by applying data preprocessing techniques.
• Visitors can perform the basic task from the front end and reply to
its queries with a binary response (yes/no).
• Afterwards the chatbot will be predicting the type of disease and
will reply back with the predicted disease as well as will also
recommend the link of the doctor associated with it.
DATASET OF DISEASE

It consist of types
of diseases and
various symptoms
associated with it.

1 : the symptom is
present

0 : the symptom is
not present.
DATASET OF DOCTORS

This dataset consist


of details of each
doctor and the link
associated with that
doctor.
The link provides the
details of the doctor
as well its contact
information.
CHATBOT FUNCTIONALITY
CONCLUSION

From my perspective, chatbots or smart assistants with


artificial intelligence are dramatically changing businesses.
There is a wide range of chatbot building platforms that are
available for various enterprises, such as e-commerce, retail,
banking, leisure, travel, healthcare, and so on.
Chatbots can reach out to a large audience on messaging apps
and be more effective than humans. They may develop into a
capable information-gathering tool in the near future.
THANK-YOU
ANY QUERIES ?

You might also like