Scribd
Upload
7 views30 pages

Dr. Dubacharla Gyaneshwar

The document provides an overview of a course on Artificial Intelligence and Data Science, covering topics such as machine learning algorithms, deep learning frameworks, and data handling tools. It includes course evaluation methods, key metrics for evaluating classification and regression tasks, and introduces concepts like accuracy, confusion matrix, and stochastic gradient descent. Additionally, it outlines the structure of the course, including quizzes, projects, and a Q&A session.

Uploaded by

sonudon161007
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views30 pages

Dr. Dubacharla Gyaneshwar

The document provides an overview of a course on Artificial Intelligence and Data Science, covering topics such as machine learning algorithms, deep learning frameworks, and data handling tools. It includes course evaluation methods, key metrics for evaluating classification and regression tasks, and introduces concepts like accuracy, confusion matrix, and stochastic gradient descent. Additionally, it outlines the structure of the course, including quizzes, projects, and a Q&A session.

Uploaded by

sonudon161007
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 30

Introduction to

Artificial Intelligence
and Data Science
by

Dr. Dubacharla Gyaneshwar


Department of Computer Science and Engineering
Indian Institute of Information Technology Raichur (IIIT-R)

ID142 - R-slot - 2024


Contents
•Course Overview
•Basics
•Artificial Intelligence
•Data Science
•Applications
•Getting started
•Q&A session
Dr. Dubacharla Gyaneshwar
Course Overview

•Introduction to AI and Data Science


•Tools for AI and Data Science
•Machine Learning Algorithms Overview
•Deep Learning Frameworks and Case
Studies
•Data Handling and Visualization Tools
Dr. Dubacharla Gyaneshwar
Course Evaluation

• Breakdown: • Dates:
• Project - 25 • 03 December - Quiz 1,
• End-semester - 35 • 09 December - Quiz 2,
• 17 to 19 - Project
• Quiz-25 (average of two
quizzes)
submission &
Demonstration
• Attendance - 5
• 22nd December End-
• Assignment - 10 semester
Dr. Dubacharla Gyaneshwar
References

Dr. Dubacharla Gyaneshwar


Glossary / Keywords / Index Terms
• Data • Algorithm
• Model • Artificial Intelligence
• Features • Data Science
• Dataset • Machine Learning
• Training • Classification
• Testing • Prediction
Dr. Dubacharla Gyaneshwar
Machine learning

Dr. Dubacharla Gyaneshwar


Classification
• Classification techniques are used to categorize data
and gain insights from it.
• The primary goal of classification is to develop or
utilize a model that can precisely assign a label or
category to a new observation based on its features.

Dr. Dubacharla Gyaneshwar


Classification

Dr. Dubacharla Gyaneshwar


Regression

, etc , etc

Dr. Dubacharla Gyaneshwar


Metrics for evaluation
Classification task
• Accuracy: The percentage of correctly predicted labels
out of total predictions.
• Precision: The ratio of correctly predicted positive
observations to the total predicted positives.
• Recall: The ratio of correctly predicted positive
observations to all observations in the actual class.
• F1 Score: The harmonic mean of precision and recall.
• ROC-AUC Score: Measures the ability of the model to
distinguish between classes.
• Confusion Matrix: A table that shows the number of
correct and incorrect predictions for each class.
Dr. Dubacharla Gyaneshwar
Model performance metrics

Dr. Dubacharla Gyaneshwar


Accuracy
Accuracy simply measures how often the classifier correctly predicts.

Dr. Dubacharla Gyaneshwar


Confusion matrix
A confusion matrix is sometimes also referred to as an error matrix. This term
reflects its role in providing a detailed breakdown of correct and incorrect
predictions in a classification problem, helping to understand the
performance of a model.

Dr. Dubacharla Gyaneshwar


Confusion matrix

Dr. Dubacharla Gyaneshwar


Confusion matrix

Dr. Dubacharla Gyaneshwar


Exercise

Dr. Dubacharla Gyaneshwar


Exercise

Dr. Dubacharla Gyaneshwar


Exercise

Dr. Dubacharla Gyaneshwar


Metrics for evaluation
Regression task
• Mean Absolute Error (MAE): The average of the absolute
errors between predicted and actual values.
• Mean Squared Error (MSE): The average of the squares of
the errors between predicted and actual values.
• Root Mean Squared Error (RMSE): The square root of the
MSE, providing error in the same units as the target.
• R-squared (R²): The proportion of the variance in the
dependent variable that is predictable from the
independent variables.
Dr. Dubacharla Gyaneshwar
Metrics for evaluation

(Sum of Squares
Regression/Total/Error)

Dr. Dubacharla Gyaneshwar


Metrics for evaluation

Dr. Dubacharla Gyaneshwar


Stochastic Gradient Descent
• Iterative optimization algorithm for
minimizing functions in machine
learning models.
• Uses small data batches for quicker
parameter updates during training.
• Efficient and scalable, suitable for large
datasets and models.
• May fluctuate more but escapes local
minima effectively.
• Includes advanced variants like Mini-
Batch, Momentum, RMSprop, Adam.

Dr. Dubacharla Gyaneshwar


Support Vector Machine

Dr. Dubacharla Gyaneshwar


Perceptron

Dr. Dubacharla Gyaneshwar


Activation Function

Dr. Dubacharla Gyaneshwar


Deep Neural Networks

Dr. Dubacharla Gyaneshwar


Deep Learning frameworks and Case Studies

• Deep learning frameworks are software


libraries or platforms that simplify the
process of building, training, and deploying
deep learning models.

Dr. Dubacharla Gyaneshwar


Q&A session

?
Dr. Dubacharla Gyaneshwar
Thank you!

Dr. Dubacharla Gyaneshwar

You might also like