Table of Content

Introduction & Suggested Prerequisites 1

Course Objective 2
Course Outcome 2
Course Level 2
Course URL 2
How the Course is useful for VIT Students 3
Course Duration in Hours 3
Course Syllabus 4, 5 & 6
Assignment & Quiz 7
Grand Assessment 7
Project Work 7
Ask Me Anything Sessions 7
Submissions 7
Evaluation 7
Certificate Generation 7
Attendance 7
Session Recordings 7
Introduction:

This course is designed to provide participants with a comprehensive understanding of data science,artificial
intelligence principles and equip them with practical skills to excel in data-driven roles. Throughout the course,
participants will learn how to use the Python programming language and essential data science,Deep Learning
libraries to manipulate, analyze, and derive insights from complex datasets.

Data science & Artificial Intelligence is a rapidly evolving field that focuses on extracting valuable information from
data to drive decision-making and solve real-world problems. In this course, we will cover a wide range of topics,
including data wrangling, exploratory data analysis, regression, classification and Deep Learning algorithms, model
evaluation, and web application development using the Flask framework.

Artificial Intelligence refers to the development of intelligent machines that can simulate human cognitive abilities.
These machines are designed to perform tasks that would typically require human intelligence, such as
understanding natural language, recognizing patterns, making decisions, and learning from data.Throughout this
course, we will cover a wide range of topics and subfields within AI. We will start by establishing a foundational
understanding of AI concepts, including machine learning, neural networks, transfer learning and computer vision

Our emphasis is on hands-on learning, where participants will have numerous opportunities to apply their
knowledge through practical exercises, projects, and real-world use cases across different industries. We believe
that practical experience is crucial for developing the skills required to excel in data science & artificial intelligence.

By the end of the course, participants will be equipped with the ability to utilize data science & artificial intelligence
techniques, tools, and best practices to extract insights, make data-driven decisions, and build predictive models.
Whether you are looking to enhance your employability, pursue further studies in data science,artificial intelligence,
or expand your skill set, this course will provide you with a solid foundation and practical experience in the field of
applied data science & artificial intelligence.

This program consists of live sessions, Hands-on practical activities, mentoring support, etc. In order to help all
beginners, understand the Programming language, web framework etc. We have curated the best modules that will
help you to get ready for the training.

Suggested Prerequisites:

Students have:

● Basic knowledge of programming language

● Basic understanding of HTML, CSS & JavaScript
● Basic Understanding of ML,DL

Please go through the below-mentioned link to install all the prerequisites. Which is necessary to attend the live
session and complete your project tasks.

Anaconda Navigator:
● Anaconda Navigator Download: https://www.anaconda.com/products/distribution
● Installation guide: https://docs.anaconda.com/free/anaconda/install/windows
VS Code:
● Download: https://code.visualstudio.com/download
● Installation guide: https://code.visualstudio.com/docs/setup/setup-overview
Html:
● Ref link : https://www.w3schools.com/html/
CSS:
● Ref link : https://www.w3schools.com/css/
JavaScript:
● Ref link: https://www.w3schools.com/js/
Course Objective:

● Gain a comprehensive understanding of Applied Data Science & Artificial Intelligence.

● Develop proficiency in the Python programming language for Data Science & Artificial
Intelligence.
● Learn to utilize essential Python packages for Data Science & Artificial Intelligence tasks.
● Acquire skills in Data Wrangling,visualization,Data Augmentation and text preprocessing,Time
series Analysis, object detection and OpenCV Concept.
● Build and evaluate Machine Learning algorithms for regression and classification tasks.
● Build and evaluate Deep Learning models.
● Develop the ability to build web applications using the Flask web framework.
● Understand fundamental mathematical concepts for Data Science, including descriptive
statistics, hypothesis testing, and regression analysis.
● Familiarize yourself with linear algebra and calculus for Data Science applications.
● Familiarize yourself with models like CNN, LSTM, RNN, YOLO, and OpenCV.
● Gain practical experience in working with data manipulation libraries (NumPy, Pandas), data
visualization libraries (Matplotlib, Seaborn), and model evaluation metrics.Working with image
data for predicting different kind of classes, text preprocessing using NLP, object detection using
advanced models like YOLO,time series analysis using RNN, LSTM, OpenCV concepts

Course Outcome:

● By the end of the course, participants should have a strong foundation in Applied Data Science &
Artificial Intelligence, Python programming, data manipulation, Machine Learning algorithms,
Data augmentation, handling image & text data for prediction, object detection,OpenCV
concepts,web application development, and data analysis. They will be equipped with the skills
necessary to tackle real-world Data Science problems and make data-driven decisions.

Course Level:

● The Artificial Intelligence & Applied Data Science course is an intermediate-level program
that provides participants with a comprehensive understanding of Artificial Intelligence & data
science concepts and practical skills in Python programming. It covers various topics such as
data wrangling, exploratory data analysis, machine learning algorithms,data augmentation,Deep
learning models, web application development, and model evaluation. The course also includes
mathematical concepts relevant to data science, including descriptive statistics and linear
algebra. By the end of the course, participants will have the ability to apply artificial intelligence &
data science techniques to real-world scenarios, make data-driven decisions, and effectively
communicate insights.

Course URL:

● Visit:- https://smartinternz.com/externship_dyn/424/applied-data-science
● Visit:- https://smartinternz.com/externship_dyn/1/artificial-intelligence
How the Course is useful for VIT Students?

The Artificial Intelligence & Applied Data Science course can be highly beneficial for VIT (Vellore Institute
of Technology) students in several ways:

● Enhancing employability: Artificial Intelligence & Data Science skills are in high demand across
industries. By acquiring proficiency in applied data science, VIT students can significantly enhance their
employability prospects. They will be equipped with the knowledge and skills required to work in
data-driven roles, such as data analyst, data scientist, machine learning engineer, and business
analyst.

● Complementing academic curriculum: The course can complement the existing academic curriculum at
VIT by providing practical and hands-on experience in Artificial Intelligence & Data Science. It offers an
opportunity for students to apply theoretical concepts learned in their coursework to real-world
scenarios, enhancing their understanding and practical skills.

● Bridging the gap between academia and industry: AI / Data science is a rapidly evolving field, and the
industry requirements often surpass the academic curriculum. By taking the "Artificial Intelligence"
course, VIT students can bridge the gap between academia and industry. They will gain exposure to the
latest tools, techniques, and best practices in AI, aligning themselves with industry expectations.

● Enabling interdisciplinary collaborations: Artificial Intelligence & Data Science is an interdisciplinary field
that intersects with various domains, including computer science, mathematics, business, and
engineering. By acquiring applied data science skills, VIT students can collaborate with students and
professionals from different disciplines, fostering interdisciplinary projects and research initiatives.

● Supporting research and innovation: Artificial Intelligence/Data science skills are invaluable for
conducting research and innovation projects. VIT students can leverage the knowledge gained from the
course to analyze large datasets, derive meaningful insights, and contribute to cutting-edge research in
their respective fields.

● Preparing for higher education: The Artificial Intelligence & Applied Data Science course can serve as a
strong foundation for VIT students who wish to pursue higher education in data science or related fields.
It equips them with the necessary skills and knowledge to excel in advanced data science programs or
research-based studies.

Course Duration:

● Course Name: Artificial Intelligence & Machine Learning

● Duration: 100 Hours
Training

We organise hands on 4 Weeks Bootcamp during your externship period to provide you practical knowledge
on the technology.

Course Syllabus:

Artificial Intelligence & Machine Learning

SNo Subject Area Topics Duration
● What is Artificial Intelligence
● History of Artificial Intelligence
● Use Cases of Artificial Intelligence
● What is data science
● Why is it important
Introduction to ● Use Cases of Data Science
1 Artificial Intelligence & ● The Various Data Science Disciplines 2
Data Science ● Data Science and Business Buzzwords
● What is the difference between Analysis
and Analytics
● ML In Data Science
● Machine Learning Tools & Packages
● Data Science Methodology
● Python Basics
● Python Packages
● Working with NUMPY
Python for Data ● Working with Pandas
2 5
Science ● Introduction to Data Visualization
● Exploratory Data Analysis with Matplotlib
and Seaborn
● Basic Plotting with Matplotlib and Seaborn
● Descriptive Statistics:
1. Introduction to descriptive
Statistics
2. Mean, Median, Mode
3. Skewness
4. Range & IQR
5. Sample vs. Population
6. Variance & Standard deviation
7. Impact of Scaling & Shifting
Mathematics for Data
3 ● Distributions: 2
Science
1. What is a distribution?
2. Normal distribution
● Z-Scores
● Central Limit Theorem
● Hypothesis Testing
● Correlation, And Regression
● Linear Algebra
● Calculus
 ● Introduction to Data preprocessing
● Importing the Dataset
● Handling Missing data
Data Wrangling
4 ● Working with categorical Data 3
Techniques
● Splitting the data into Train and Test set
● Outlier Analysis
● Feature Scaling
● Introduction to Regression
● Linear Regression
Supervised Learning – ● Multi Linear Regression
5 5
Regression ● Polynomial Regression
● Ridge Regression
● Lasso Regression
● Introduction to Classification
● Logistic Regression
● Decision Tree Classification
Supervised Learning - ● Random Forest Classification
6 8
Classification ● K-nearest Neighbors
● Naïve-Bayes
● Support Vector Machine
● Ensembling Techniques
● Regression Evaluation Metrics
1. MAE
2. MSE
3. R Squared
4. RMSE
Model Evaluation
7 ● Classification metrics 3
Metrics
1. Confusion Metrics
2. Accuracy
3. Precision
4. Recall F1 Score
5. AUC ROC Curves
● Handling Imbalanced Data
1. Oversampling
2. Undersampling
Hyper-parameter 3. Ensembling Techniques
8 3
Optimization 4. SMOTE
● Hyper-parameter tuning
1. Grid Search
2. Randomize Search
● Introduction to Clustering
Unsupervised 1. K-Means Clustering
9 3
Learning 2. Hierarchical Clustering
3. Clustering use cases
● The Neuron
● The Activation Function
● How do Neural Networks work?
Introduction to Neural ● How do Neural Networks learn?
10 3
Networks
● Gradient Descent
● Stochastic Gradient Descent
● Backpropagation
 ● Introduction to Tensorflow & Keras
Framework
● Introduction to the Sequential Mode
● Activation functions
11 Tensorflow & Keras ● Layers 3
● Training
● Loss function
● Building ANN Using Tensor flow
● Evaluating Improving and Tuning ANN
● Introduction to Convolutional Neural
Networks
● What are convolutional neural networks?
● Step 1 - Convolution Operation
● Step 2 - Pooling
● Step 3 - Flattening
Convolutional Neural
12 ● Step 4 - Full Connection Classification of 10
Networks
images using CNN
● Evaluating, Improving, and Tuning the
CNN
● Video Analysis using OpenCV
● Object detection using YOLO

● Introduction to Recurrent Neural

Networks
● The idea behind Recurrent Neural
Networks
● The Vanishing Gradient Problem
Recurrent Neural
13 ● LSTMs 3
Networks
● LSTM Variations Predicting Google
stock prices using RNN
● Evaluating, Improving, and Tuning
the RNN

● Introduction to Natural Language

Processing
● Introduction to NLTK
Natural Language ● Bag of Words model
14 3
Processing ● Natural Language Processing in
Python
● Sentiment analysis using Natural
Language Processing
● Introduction to different modes of
deployment
● Working with Flask Framework
Build & Deploy ML ● Building application with flask framework
15 ● Integrating Machine Learning model with 4
Application
web application
● Integrating Deep learning model with Web
Application
Assignment & Quiz
As part of the training program, we will be assigning assignments and quizzes every 10 hours. These
assignments and quizzes are designed to help you learn and understand the concepts being covered in the
training.

Grand Assessment
We will be conducting a grand assessment after completing the training sessions to evaluate your overall
performance and understanding of the concepts covered in the training.

Project Work
Students need to work on their selected project based after completing the training session and complete their
project task on time for successful submission.

Ask Me Anything Sessions

After assigning the projects for the learners, if they face any challenge in completion of the milestones, activities
we will organize Ask Me Anything (AMA) sessions to address the queries, learners have daily AMA sessions for 1
hour to solve the queries.

Submissions

Each learner’s journey and completion status is tracked through SmartInternz platform. learners will be asked to
update the status of their work regularly to track their progress and assist accordingly.

Evaluation

We will verify the progress of each learner on the SmartInternz platform. It is mandatory for all the learners to
complete the all the milestones, project tasks and submit successfully on platform.

Certificate Generation

After successful verification of your project by evaluator, then team will generate the certificate for students.

Attendance

The Learner needs to maintain a 75% attendance.

Session Recordings

Session Recording will be available in Smartbridge teachable platform.