1

9/9/2023

SNS COLLEGE OF ENGINEERING

Kurumbapalayam(Po), Coimbatore – 641 107
(An autonomous institution)
Accredited by NAAC-UGC with ‘A’ Grade
Approved by AICTE, Recognized by UGC & Affiliated to Anna University, Chennai

Mrs. [Link]/Assistant Professor

DEPARTMENT OF ARTIFICIAL INTELLIGENCE & DATASCIENCE

N.Padmashri_basic concepts_AI&DS
 Basic Concepts in Machine Learning

➢ Machine Learning is defined as a technology that is used to train machines to

perform various actions such as predictions, recommendations, estimations, etc.,
based on historical data or past experience.

➢ Machine Learning enables computers to behave like human beings by training

them with the help of past experience and predicted data.

➢ There are three key aspects of Machine Learning, which are as follows:

9/9/2023 N.Padmashri_basic concepts_AI&DS 2

 There are three key aspects of Machine
Learning
➢ Task: A task is defined as the main problem in which we are interested. This
task/problem can be related to the predictions and recommendations and
estimations, etc.
➢ Experience: It is defined as learning from historical or past data and used to
estimate and resolve future tasks.
➢ Performance: It is defined as the capacity of any machine to resolve any
machine learning task or problem and provide the best outcome for the
same. However, performance is dependent on the type of machine learning
problems.

9/9/2023 N.Padmashri_basic concepts_AI&DS 3

 Techniques in Machine Learning

✓ Supervised Learning
✓ Unsupervised Learning
✓ Reinforcement Learning
✓ Semi-supervised Learning(is an intermediate technique of both supervised
and unsupervised learning)

9/9/2023 N.Padmashri_basic concepts_AI&DS 4

 Applications of Machine Learning

9/9/2023 N.Padmashri_basic concepts_AI&DS 5

 Machine Learning Process

➢ Machine learning is the process of making systems that learn and

improve by themselves, by being specifically programmed.

➢ The ultimate goal of machine learning is to design algorithms that

automatically help a system gather data and use that data to learn more.

9/9/2023 N.Padmashri_basic concepts_AI&DS 6

 Steps In Developing A ML Application.

1. Gathering data
2. Preparing that data
3. Choosing a model
4. Training
5. Evaluation
6. Hyper parameter tuning
7. Prediction
 Case Study :
1. Price Comparison Tool: The tool will allow you to compare similar
products offered online by different brands and retailers by web scraping.
You can compare the prices of your desired products and pay the lowest
price to buy them. The tool will also send a notification about the company
with the lowest price, along with a link that can be used to buy the product.
2. Crime Analysis: Our Crime Analysis project creates a website showcasing
crime data insights. The website will serve as a valuable resource for law
enforcement agencies, policymakers, and the general public, aiding in
evidence-based decision-making and the development of targeted crime
prevention strategies.
3. Disease Detection
4. Disease Prevention
Steps In Developing A ML Application.
Objective/Define Problem/ Hypothesis

1. Gathering data
2. Preparing that data
3. Choosing a model
4. Training
5. Evaluation
6. Hyper parameter tuning
7. Prediction
 Define the Problem:

1. Clearly define the problem you want to solve using

machine learning.
2. Identify the goals, requirements, and desired outcomes
of the application.
3. This step involves understanding the problem domain,
gathering relevant data, and defining the evaluation
metrics for measuring success.
 Price Crime Analysis
Comparison Tool
Clearly define the problem and the Clearly define the problem and the
objectives of the Price Comparison Tool. objectives of the Crime Analysis project.

Develop a tool that allows users to Develop a website that showcases crime
compare prices of similar products data insights to support law enforcement
offered by different brands and retailers, agencies, policymakers, and the general
enabling them to find the lowest price public. The project aims to provide
and make informed purchasing decisions. evidence-based decision-making and aid
in the development of targeted crime
prevention strategies.
 Steps In Developing a ML Application.

1. Gathering data
This step is very important because the quality and quantity of data that you gather will
directly determine how good your predictive model can be.

• Investigate and obtain data that you will use to feed your machine.

• The quality and quantity of data

• Existing dataset

• Develop your own datasets ( survey forms/experiments)

• Web scraping technique to automatically collect information from various sources

such as APIs.
 Price Crime Analysis
Comparison Tool
Collecting relevant data is crucial for the Collecting relevant crime data is crucial
tool's functionality. In this case, web for the project's functionality. Identify
scraping can be used to gather product reliable sources for crime data, such as
information, including prices, from law enforcement agencies, government
various e-commerce websites. Identify databases, or publicly available crime
the target websites and determine the data repositories. Gather information on
data attributes to be extracted, such as various crime-related variables, such as
product name, brand, retailer, and price. location, date/time, type of crime, and
other relevant attributes.
 Steps In Developing A ML Application.
2. Preparing that data
i. Not all the collected data is useful for a machine learning application.

ii. We may need to clean the irrelevant data, which may affect the
accuracy of prediction or may take additional computation without
aiding in the result.

iii. Once the data ready for the machine learning algorithm, we need to
transform the data in the form that the ML system can understand.

iv. Machines cannot understand an image or text. We need to convert it

into numbers.

v. It also requires building data pipeline depending on the machine

learning application needs.
 Price Crime Analysis
Comparison Tool
Preprocess the collected data to ensure Preprocess the collected crime data to
its quality and compatibility with the ensure its quality and compatibility with
machine learning model. This involves the machine learning model. This
cleaning the data, handling missing involves cleaning the data, handling
values, standardizing formats, and missing values, standardizing formats,
resolving any inconsistencies. and resolving any inconsistencies.
Additionally, perform any necessary data Additionally, perform any necessary data
transformations or feature engineering to transformations or feature engineering to
extract relevant features for the model. extract meaningful features for the
model.
 Steps In Developing A ML Application.
3. Choosing Model
• Choose an appropriate machine learning algorithm to build the price
comparison model. This could involve techniques such as natural
language processing (NLP) for text analysis, clustering or similarity
algorithms for product matching, or regression models for price
prediction. The choice of model depends on the specific requirements
and characteristics of the data.

Model Applications
Logistic Regression Price prediction
Fully connected networks Classification
Convolutional Neural Networks Image processing
Recurrent Neural Networks Voice recognition
Random Forest Fraud Detection
Reinforcement Learning Learning by trial and error
Generative Models Image creation
K-means Segmentation
k-Nearest Neighbors Recommendation systems
Bayesian Classifiers Spam and noise filtering
 Price Crime Analysis
Comparison Tool
Choose an appropriate machine learning Choose appropriate machine learning
algorithm to build the price comparison algorithms or techniques to build models
model. This could involve techniques for crime analysis. This can involve
such as natural language processing (NLP) techniques such as clustering to identify
for text analysis, clustering or similarity crime hotspots, classification for
algorithms for product matching, or predicting crime types or severity, or
regression models for price prediction. anomaly detection for identifying
The choice of model depends on the unusual patterns. The choice of models
specific requirements and characteristics depends on the specific requirements
of the data. and objectives of the project.
 Steps In Developing A ML Application.

4. Training
• The goal of training is to answer a question or make a prediction
correctly as often as possible.
• Linear regression example: algorithm would need to learn values
for m (or W) and b (x is input, y is output)
• Each iteration of process is a training step

• Split the preprocessed data into training and validation sets. Use
the training set to train the machine learning model on historical
data, including product information and prices. Validate the
model's performance using the validation set to assess its
accuracy and generalization capabilities
 Price Crime Analysis
Comparison Tool
Split the preprocessed data into training Split the preprocessed data into training
and validation sets. Use the training set and validation sets. Use the training set
to train the machine learning model on to train the machine learning models on
historical data, including product historical crime data. Validate the
information and prices. Validate the models' performance using the validation
model's performance using the validation set to assess their accuracy, precision,
set to assess its accuracy and recall, or other relevant metrics.
generalization capabilities. Iteratively Iteratively refine the models by adjusting
refine the model by adjusting hyperparameters and evaluating their
hyperparameters and evaluating its performance.
performance.
 Steps In Developing A ML Application.

5. Evaluation
• Uses some metric or combination of metrics to
"measure" objective performance of model.
• Test the model against previously unseen data.
• This unseen data is meant to be somewhat
representative of model performance in the real
world, but still helps tune the model (as opposed to
test data, which does not).
• Good train/eval split? 80/20, 70/30, or similar,
depending on domain, data availability, dataset
particulars, etc.
 Steps In Developing A ML Application.
6. Hyper parameter Tuning
• Once the evaluation is over, any further improvement in your training
can be possible by tuning the parameters.
• There were a few parameters that were implicitly assumed when the
training was done.
• Another parameter included is the learning rate that defines how far
the line is shifted during each step, based on the information from
the previous training step.
• These values all play a role in the accuracy of the training model, and
how long the training will take.
• Tune model parameters for improved performance
• Simple model hyper parameters may include: number of training
steps, learning rate, initialization values and distribution, etc.
 Steps In Developing A ML Application.

7. Prediction
Using further (test set) data which
have, until this point, been withheld
from the model (and for which class
labels are known), are used to test the
model; a better approximation of how
the model will perform in the real
world.