Scribd
Upload
31 views

Machine Learning (Autosaved)

The document summarizes a technical seminar presentation on machine learning models. It discusses how machine learning focuses on developing computer programs that can learn from data without being explicitly programmed. It then provides a 3-step process for creating machine learning models: 1) data preparation which involves cleaning and formatting data, 2) data modeling where a model is created using a learning algorithm like supervised, unsupervised, or reinforcement learning, and 3) performance measurement by predicting labels and cross-validating outputs. Finally, it lists some applications of machine learning like image recognition, speech recognition, virtual assistants, and language detection.

Uploaded by

BHARGAVA REDDY
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
31 views

Machine Learning (Autosaved)

The document summarizes a technical seminar presentation on machine learning models. It discusses how machine learning focuses on developing computer programs that can learn from data without being explicitly programmed. It then provides a 3-step process for creating machine learning models: 1) data preparation which involves cleaning and formatting data, 2) data modeling where a model is created using a learning algorithm like supervised, unsupervised, or reinforcement learning, and 3) performance measurement by predicting labels and cross-validating outputs. Finally, it lists some applications of machine learning like image recognition, speech recognition, virtual assistants, and language detection.

Uploaded by

BHARGAVA REDDY
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

Department of Electronics and Communication Engineering

Technical seminar topic on


“Machine Learning Model”

BY:-V.DINESH KUMAR RAJU


ROLL NO:-18701A0428
Machine Learning
• Machine learning is an application of artificial intelligence (AI) that provides systems
the ability to automatically learn and improve from experience without being
explicitly programmed.
• Machine learning focuses on the development of computer programs that can access
data(bigdata and programs) and use it learn for themselves.

1
• In traditional programming program is developed by programmers and output is
generated by the system.
2

In machine learning programs are created explicitly by the computer and these
programs are enhanced by itself and increase the probability of getting relevant
output.

Eg:-virtual assistants ,voice recognition , google lens e.t.c


How machine learning model created?
Data preparation:-
 Raw data:-It contains text, images or videos, binary data and others. This data contains
both useful and unwanted data which is used to prepare a model .
 Query data:-The query data can be done by pandas which is a python library which is
the process where entire data is ordered into subsets and creating a data frame work.
 Cleaning data:-
* Dealing with missing values
* removing outliers

 Arranging or format data:-In this data is modified so that it fits to constraints of algorithms.
*The most common transformation is encoding into categorical variables this overall
process is done by data architect.

 This clean dataset is used for Feature Engineering which is the next process in making a
model where the model is created with inputs so that algorithm can understand.
Data modelling :-
 Now the data is used to train a model using a learning algorithm.
Machine learning

Supervised Unsupervised Semi supervised Reinforcement


classification clustering learning learning

 Supervised learning :- Data which is well labeled that means some data is already
tagged with the correct answer. Learning from the know label data to create a model
then predicting target output for the given input data
Example:-
Unsupervised learning:-
 Algorithm using information that is neither classified nor labeled and allowing the
Algorithm to act on that information without guidance.
Example:-
Semi supervised learning:-
 Semi-supervised learning is a class of machine learning tasks and techniques that also
make use of unlabeled data for training – typically a small amount of labeled
data with a large amount of unlabeled data. Semi-supervised learning falls
between unsupervised learning (without any labeled training data) and supervised
learning (with completely labeled training data).
Reinforcement learning:-
 It is about taking suitable action to maximize reward in a particular situation. It is
employed by various software and machines to find the best possible behavior or
path it should take in a specific situation.
 Decision process, reward system and learn series of action.
 Supervised learning need data in labeled format so data must be labeled which is
very complicated in case of huge data.
 Unsupervised learning algorithms don’t need labeled data but the training phase
takes huge number of cases the more number of relevant inputs the higher the
efficiency of output.
 Semi supervised learning method contains small labeled data compared to
unlabeled data so desired output have higher efficiency than unsupervised
learning.
 Reinforcement learning depends on agents which are program mentors that can
provide reward means if the output is relevant then it rewards to save the changes
in algorithm itself but if the output is not relevant then nothing works correctly so
decision process is the key step in learning of reinforcement learning.
Performance measure:-
 Predicting data set labels
a)training set and data set
b)cross validation of output with human efforts or programs.

 Choosing performance indicator based on the algorithm


*regressions
*classification
Few applications of machine learning :-

image recognition.

speech or voice recognition.

sales and marketing applications like amazon.

Virtual assistants like google assistant , google lens

language detection

cloud server technologies

search engines for website retargeting


THANK YOU

You might also like