Syllabus (AI - ML BlackBelt Plus Program)
Syllabus (AI - ML BlackBelt Plus Program)
Syllabus (AI - ML BlackBelt Plus Program)
• Use Matplotlib and Seaborn for data Data exploration and Statistical Inference are
visualization one of the initial and important steps in the
• Create charts to visualize data and analysis process. This module will take you
generate insights through the process of exploring your data
• Univariate and Bivariate analysis with the help of interactive visualizations and
using python insight generation so that you can get the
• Perform Statistical Analysis on real- bigger picture of your data. Learn to draw
world datasets statistical conclusions to discover the
• Build and Validate Hypothesis using unknown aspects of data with the help of
statistical tests various statistical tests
• Generate useful insights from the
data Pre-requisites
This module requires knowledge of
Python.
3. Storytelling and Dashboarding
Case Study
• Predicting the NYC taxi trip duration
• Customer churn prediction
Pre-requisites
This Module requires prior knowledge of
Python, Statistics and Exploratory Data
Analysis (EDA).
5. Feature Selection and Engineering
• Learn the art of Feature engineering Feature Engineering plays a crucial role in
• Feature Generation from time-series data improving the quality of your ML model. In
• Automated Feature Engineering Tool this module, you’ll go through various
• Concept of dimensionality reduction feature selection and engineering
• Feature Selection and Elimination techniques that can help you create/extract
Techniques new features from a given dataset and
select a subset of relevant features for your
• Detailed Understanding of Principal
model that can yield better results.
Component Analysis (PCA)
• Concept of Factor Analysis
Pre-requisites
This Module requires prior knowledge of
Python, EDA and Basic Machine Learning.
6. Advanced Machine Learning
• Explore the Advanced ML concepts and Till now, you would have developed a good
Algorithms understanding of Basics of Machine
• Use Ensemble Learning Techniques Learning and Feature Selection techniques.
(Stacking and Blending) Now, it’s time to dive deeper into the
• Understand and Implement Bagging and advanced ML concepts and algorithms. This
Boosting Algorithms module focuses on how you can further
• Learn to handle Text data and Image improve your model by using ensemble
Data learning, how to handle text and image data
• Work with structured and unstructured and then finally an introduction to
data unsupervised learning problems.
• Learn to deal with unsupervised learning
problems Case Study
• Clustering Algorithms including k-means • Web Page Classification
and Hierarchical clustering • Malaria Detection from Blood cell images
Pre-requisites
This Module requires prior knowledge of
Python, Statistics, EDA and Basic Machine
Learning
7. Problem Formulation and Communication
Pre-requisites
This Module requires prior knowledge of
Basic Machine Learning.
8. Deep Learning
• Important concepts of Deep What is deep learning? How can you get
learning started with deep learning? This
• Working of Neural Network comprehensive module will provide you with
from Scratch everything you need to know about deep
• Activation Functions and learning with Python, including a deep dive
Optimizers for Deep into neural networks! Deep learning
Learning algorithms are powered by techniques like
• Understand Deep Learning Convolutional Neural Networks (CNN),
architectures (MLP, CNN, RNN and Recurrent Neural Networks (RNN), Long
more) Short Term Memory (LSTM), etc. and we will
• Explore Deep Learning cover each one of them and see how they
Frameworks like Keras and can solve real life problems.
PyTorch
• Learn to tune the
Case Study
hyperparameters of Neural
Networks • Predict whether the loan should be
• Build Deep Learning approved or not
models to tackle real-life
• Classify Emergency Vehicles from Non-
problems.
Emergency Vehicle
• Auto tagging Stack Overflow Queries
Pre-requisites
This Module requires prior knowledge of
Python and Basic Machine Learning.
9. Computer Vision using PyTorch
• Get familiar with the world of Computer This module is designed to give you a taste
Vision of how the underlying techniques work in
• Transfer Learning for Computer Vision current State - of -the - Art Computer Vision
• Work with popular Deep Learning systems and walks you through a few of the
Framework - Pytorch remarkable Computer Vision applications in
• Learn State-of-the-art Algorithms like a hands - on manner so that you can create
YOLO, SSD, RCNN and more
such solutions on your own.
• Work on different types of problems
• Build Face Detection and Pose
Detection Models PyTorch has helped accelerate the research
• Advanced CV Problems like Image that goes into deep learning models by
Segmentation and Image Generation making them computationally faster and less
• Understand how GANs work expensive (a data scientist’s dream!). You
will work with PyTorch for computer vision’s
tasks like image classification, object
detection, pose detection and much more.
You will quickly find yourself leaning on
PyTorch’s flexibility and efficiency for
computer vision.
Case Study
• Classify Emergency Vehicles from
Non-Emergency Vehicles
• Identify the Location of Red Blood
Cells
• Building a model to detect faces
from images
• Lane Segmentation for self driving
cars
Pre-requisites
This Module requires prior knowledge of
Python, Basic Machine Learning and
Fundamentals of Deep Learning.
10. Getting started with NLP
Pre-requisites
This Module requires prior knowledge of
Python and Basic Machine Learning
11. NLP using Deep Learning
Pre-requisites
This Module requires prior knowledge of
Python, Basic Machine Learning, and
Fundamentals of Deep Learning
12. Recommendation Systems
Pre-requisites
This Module requires prior knowledge of
Python, Basic Machine Learning, and
Fundamentals of Deep Learning
13. Time Series using Python
Pre-requisites
This Module requires prior knowledge of
Python, and Basic Machine Learning.
14. Career-oriented services and Data Science
Interviews
• Understanding the different roles in This module will help you to know more about
Data Science different roles in data science, build your strong
• Dos and Don'ts for Resume resumes and prepare for data science
Building interviews. This module has been created based
• Tips and strategies to build the on hundreds of interviews we have taken,
perfect resume companies we have helped in data science
• Preparing for Data Science interviews and several data science experts in
Interviews the industry.
• Understanding the important skills
required Downloadable Resources
• How to build your digital Presence • This Infographic for 7 step processes
• Tips and Tricks to Ace Data to "Ace Data Science Interviews"
Science Resume • e-book containing more than 240
• List of Interview Questions for Data interview questions from interviews in
Science industry.
• Interview Questions on machine
learning, statistics, Model building,
Machine Learning production, SQL.
• Checklist for your LinkedIn and
GitHub profiles
15. Advanced Python and Software Engineering
Fundamentals
• What is Big Data and its In this course on Model Deployment, In this
challenges? module, we will learn about Big Data, its
applications and its challenges. How Spark
• Introduction to Apache Hadoop
helps us in dealing with Big Data? We will
• Introduction to Apache Spark
be covering the architecture of spark, its
• Deep Dive into Spark
internal working and optimization
• RDDs in Spark
techniques. We will learn how to use the
• DataFrames in Spark
different Spark APIs like Spark SQL, Spark
• Understanding Spark Execution ML using Python.
• Advance Programming in Spark
• Spark SQL
• Spark ML Pipelines in Spark Pre-requisites
The course requires you to know Basic
Python and SQL.
17. Deploying ML/DL Models
• Overview and aspects of Model In this module on Model Deployment, you will
Deployment learn how to deploy models from different
• Deploying Machine Learning domains ranging from Machine Learning to
models using Streamlit Deep Learning, Natural Language Processing
• Introduction to Amazon Web (NLP) to Computer Vision (CV). To explain
services concepts of Model Deployment, we will cover
• Deploying and Machine Learning a range of real-life projects from various
Deep Learning models using AWS industries like Banking, Healthcare, and much
• Understanding Amazon more. You will also learn different tools used
Sagemaker for Model Deployment with hands-on
• Model Deployment using experience.
Sagemaker
• APIs for Model deployment Case Study
Pre-requisites
• This Module requires prior knowledge of
Python, Basic Machine Learning,
Fundamentals of Deep Learning and
Basic Natural Language Processing.