ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
OVERALL COURSE OBJECTIVES: Equip participants with a comprehensive understanding of Machine
Learning, Artificial Intelligence, and the management of relevant projects, enabling them to
cognitively apply various models for problem-solving, create AI-powered chatbots, and effectively
deal with both supervised and unsupervised learning scenarios, hence fostering a holistic command
over the entire ML/AI landscape.
LEARNING OUTCOMES: On successful completion of the course the students shall be able to:
1. Understand and implement various machine learning models using Pytorch and other open-
source libraries.
2. Learn to manage and organize machine learning projects from inception to production using
best practices.
3. Understand the concepts and applications of Artificial Intelligence (AI) and successfully
complete a mini-project illustrating AI in action.
4. Create interactive chatbots using IBM Watson's Natural Language Processing capabilities
without the need for programming.
5. Apply supervised machine learning techniques such as logistic regression, decision trees, and
ensemble methods for classification and regression tasks.
6. Understand and implement unsupervised machine learning techniques using various
clustering and dimension reduction algorithms.
Introduction to Machine Learning
ML Foundations Managing Machine Learning Projects
Introduction to Artificial Intelligence (AI)
Building AI Powered Chatbots Without
Programming
AI & ML Algorithms – I Supervised Machine Learning: Classification
Supervised Machine Learning: Regression
AI & ML Algorithms – I Unsupervised Machine Learning
Deep Learning and Reinforcement Learning
Applied ML Machine Learning Capstone
Exploratory Data Analysis for Machine Learning
Applied AI with DeepLearning
Advanced Machine Learning and Signal
ML Applications & Data Analysis Processing
COURSE CONTENT:
Module 1: Introduction to Machine Learning [26 Hours]
This course will provide you with a foundational understanding of machine learning models (logistic
regression, multilayer perceptrons, convolutional neural networks, natural language processing, etc.)
as well as demonstrate how these models can solve complex problems in a variety of industries,
from medical diagnostics to image recognition to text prediction. In addition, we have designed
practice exercises that will give you hands-on experience implementing these data science models
on data sets. These practice exercises will teach you how to implement machine learning algorithms
with PyTorch, open source libraries used by leading tech companies in the machine learning field
(e.g., Google, NVIDIA, CocaCola, eBay, Snapchat, Uber and many more).
Sub-Topics
Simple Introduction to Machine Learning
Basics of Model Learning
Image Analysis with Convolutional Neural Networks
Recurrent Neural Networks for Natural Language Processing
The Transformer Network for Natural Language Processing
Introduction to Reinforcement Learning
Formative Assessments:
4 graded quizzes and 11 ungraded lab assignments.
Module 2: Managing Machine Learning Projects [18 Hours]
The course in the AI Product Management Specialization that centers on managing practical aspects
of machine learning (ML) projects. This course provides a thorough understanding of the integral
steps of an ML project, beginning from the identification of valuable ML opportunities, right through
to data collection, model building, deployment, as well as monitoring and maintaining production
systems. It offers insight into the fundamental processes of data science and how to effectively
organize ML projects. On successful completion of this course, participants are expected to acquire
the ability to identify potential applications of ML for problem-solving and learn about important
technological decisions in designing ML systems, along with leading ML projects from inception to
production using best practices.
Sub-Topics
Identifying Opportunities for Machine Learning
Organizing ML Projects
Data Considerations
Simple Introduction to Machine Learning
ML System Design & Technology Selection
Model Lifecycle Management
Formative Assessments:
5 graded quizzes and 1 peer review assignment.
Module 3: Introduction to Artificial Intelligence (AI) [8 Hours]
In this course you will learn what Artificial Intelligence (AI) is, explore use cases and applications of
AI, understand AI concepts and terms like machine learning, deep learning and neural networks. You
will be exposed to various issues and concerns surrounding AI such as ethics and bias, & jobs, and
get advice from experts about learning and starting a career in AI. You will also demonstrate AI in
action with a mini project.
This course does not require any programming or computer science expertise and is designed to
introduce the basics of AI to anyone whether you have a technical background or not.
Sub-Topics
What is AI? Applications and Examples of AI
AI Concepts, Terminology, and Application Areas
AI: Issues, Concerns and Ethical Considerations
The Future with AI, and AI in Action
Formative Assessments:
4 graded quizzes and 1 peer review assignment.
Module 4: Building AI Powered Chatbots Without Programming [12 Hours]
This course will teach you how to create useful chatbots without the need to write any code.
Leveraging IBM Watson's Natural Language Processing capabilities, you'll learn how to plan,
implement, test, and deploy chatbots that delight your users, rather than frustrate them.
True to our promise of not requiring any code, you'll learn how to visually create chatbots with
Watson Assistant (formerly Watson Conversation) and how to deploy them on your own website
through a handy WordPress plugin. New jobs requiring this specific skill are being added every day,
consultants demand premium rates, and the interest in chatbots is quickly exploding. Gartner
predicts that by 2020, 85% of customer interactions with the enterprise will be through automated
means (that's chatbots and related technologies).
Sub-Topics
Introduction to Chatbots
Working with Intents
Entities
Dialog
Deployment
Context Variables & Slots
Digressions
Final Exam
Formative Assessments:
8 graded quizzes.
Module 5: Supervised Machine Learning: Classification [25 Hours]
This course provides an introduction to one of the major types of supervised Machine Learning
models: Classification. It educates you on how to train models to classify categorical outcomes and
use error metrics to compare different models. The hands-on section is geared towards utilizing best
practices for classification, including train/test splits and dealing with unbalanced classes in data
sets. Upon completion, you should be able to explore and apply various classification ensembles and
models like logistic regression, decision trees, and other ensemble methods, and also use various
error metrics to identify the best model for your data. Techniques like oversampling and
undersampling to handle unbalanced classes will also be covered. This course is designed for aspiring
data scientists seeking hands-on experience with Supervised Machine Learning Classification
techniques in a business context. To get the most out of this course, you should have a basic
understanding of the Python programming environment, Data Cleaning, Exploratory Data Analysis,
Calculus, Linear Algebra, Probability, and Statistics.
Sub-Topics
Logistic Regression
K Nearest Neighbors
Support Vector Machines
Decision Trees
Ensemble Models
Modeling Unbalanced Classes
Formative Assessments:
6 graded quizzes and 1 peer-review assignment.
Module 6: Supervised Machine Learning: Regression [21 Hours]
This course presents comprehensive knowledge of supervised Machine Learning with a focus on one
of its primary modeling families: Regression. You will learn to train regression models to predict
continuous outcomes, using error metrics to compare different models. The modules include best
practices such as train and test splits along with regularization techniques. The skills that you should
expect to gain include distinguishing applications of classification and regression, applying linear
regression models, identifying the ideal linear regression model through error metrics,
understanding the necessity of regularization to prevent overfitting, and utilizing regularization
regressions like Ridge, LASSO, and Elastic net. It is targeted at aspiring data scientists wishing to gain
practical experience with Supervised Machine Learning Regression techniques in business.
Familiarity with a Python development environment and fundamental understanding of data
cleaning, exploratory data analysis, calculus, linear algebra, probability and statistics will ensure
maximum benefit from this course.
Sub-Topics
Introduction to Supervised Machine Learning and Linear Regression
Data Splits and Polynomial Regression
Cross Validation
Bias Variance Trade off and Regularization Techniques: Ridge, LASSO, and Elastic Net
Regularization Details
Final Project
Formative Assessments:
5 graded quizzes and 1 peer-review assignment.
Module 7: Unsupervised Machine Learning [23 Hours]
This course focuses on Unsupervised Learning, one of the major types of Machine Learning. It
teaches you to derive insights from data sets without a target or labeled variable using various
clustering and dimension reduction algorithms. Upon completion, you'd be able to understand the
types of problems suitable for Unsupervised Learning, comprehend the concept of dimensionality
curse and its impact on clustering, and apply common clustering and dimensionality reduction
algorithms. You'll also be able to perform clustering where necessary, compare per-cluster models,
and understand metrics important for characterizing clusters. This course is suitable for aspiring data
scientists wishing to gain practical experience in Unsupervised Machine Learning in a business
context. Familiarity with the Python programming environment, Data Cleaning, Exploratory Data
Analysis, Calculus, Linear Algebra, Probability, and Statistics will be advantageous.
Sub-Topics
Introduction to Unsupervised Learning and K Means
Distance Metrics & Computational Hurdles
Selecting a Clustering Algorithm
Dimensionality Reduction
Nonlinear and Distance-Based Dimensionality Reduction
Matrix Factorization
Final Project
Formative Assessments:
6 graded quizzes and 1 peer-review assignment.
Module 8: Deep Learning and Reinforcement Learning [32 Hours]
This course will provide you a foundational understanding of machine learning models (logistic
regression, multilayer perceptrons, convolutional neural networks, natural language processing, etc.)
as well as demonstrate how these models can solve complex problems in a variety of industries,
from medical diagnostics to image recognition to text prediction. In addition, we have designed
practice exercises that will give you hands-on experience implementing these data science models
on data sets. These practice exercises will teach you how to implement machine learning algorithms
with PyTorch, open source libraries used by leading tech companies in the machine learning field
(e.g., Google, NVIDIA, CocaCola, eBay, Snapchat, Uber and many more).
Sub-Topics
Introduction to Neural Networks
Back Propagation Training and Keras
Neural Network Optimizers
Convolutional Neural Networks
Transfer Learning
Recurrent Neural Networks and Long-Short Term Memory Networks
Autoencoders
Generative Models and Applications of Deep Learning
Reinforcement Learning
Formative Assessments:
9 graded quizzes and 1 peer-review assignment.
Module 9: Machine Learning Capstone [19 Hours]
This course enables learners to build a dynamic course recommender system utilizing Python-based
machine learning libraries like Pandas, scikit-learn, and Tensorflow/Keras. Participants will be
involved in the analysis of course-related datasets, constructing a similarity matrix using cosine
similarity, and the development of recommendation systems employing KNN, PCA, and non-negative
matrix collaborative filtering. The course lets you predict course ratings by training a neural network
and crafting regression and classification models. A crucial part of the course involves learners
creating a Streamlit app showcasing their work, following which they share and evaluate each
other's projects.
Sub-Topics
Capstone Overview
Exploratory Data Analysis and Feature Engineering
Unsupervised-Learning Based Recommender System
Supervised-Learning Based Recommender Systems
Share and Present Your Recommender Systems
Final Submission
Formative Assessments:
3 graded quizzes and 1 peer-review assignment.
Module 10: Exploratory Data Analysis for Machine Learning [14 Hours]
This course begins with an introduction to Machine Learning and its constituent content,
emphasizing the importance of high-quality data. The course facilitates learning about the retrieval
of data from multiple sources, data cleaning, feature engineering, and preliminary analysis for
hypothesis testing. Participants develop the skills to retrieve data from SQL, NoSQL databases, APIs,
Cloud, handle categorical and ordinal features, missing values, and manage outliers. It also
underscores the relevance of feature scaling and practices various scaling techniques. The course is
ideal for aspiring data scientists interested in gaining practical experience in Machine Learning and
Artificial Intelligence in a business context. To maximize the benefits, participants should be familiar
with Python programming and possess a foundational understanding of Calculus, Linear Algebra,
Probability, and Statistics.
Sub-Topics
A Brief History of Modern AI and its Applications
Retrieving and Cleaning Data
Exploratory Data Analysis and Feature Engineering
Inferential Statistics and Hypothesis Testing
Formative Assessments:
4 graded quizzes and 1 peer-review assignment.
Module 11: Applied Machine Learning in Python [31 Hours]
This course will introduce the learner to applied machine learning, focusing more on the techniques
and methods than on the statistics behind these methods. The course will start with a discussion of
how machine learning is different than descriptive statistics, and introduce the scikit learn toolkit
through a tutorial. The issue of dimensionality of data will be discussed, and the task of clustering
data, as well as evaluating those clusters, will be tackled. Supervised approaches for creating
predictive models will be described, and learners will be able to apply the scikit learn predictive
modelling methods while understanding process issues related to data generalizability (e.g. cross
validation, overfitting). The course will end with a look at more advanced techniques, such as
building ensembles, and practical limitations of predictive models. By the end of this course,
students will be able to identify the difference between a supervised (classification) and
unsupervised (clustering) technique, identify which technique they need to apply for a particular
dataset and need, engineer features to meet that need, and write python code to carry out an
analysis.
Sub-Topic
Fundamentals of Machine Learning - Intro to SciKit Learn
Supervised Machine Learning - Part 1 & 2
Formative Assessments:
4 graded quizzes and 10 programming assignments/labs.
Module 12: Applied Social Network Analysis in Python [26 Hours]
This course will introduce the learner to network analysis through tutorials using the NetworkX
library. The course begins with an understanding of what network analysis is and motivations for
why we might model phenomena as networks. The second week introduces the concept of
connectivity and network robustness. The third week will explore ways of measuring the importance
or centrality of a node in a network. The final week will explore the evolution of networks over time
and cover models of network generation and the link prediction problem.
Sub-Topics
Why study Networks and Basics on NetworkX
Network Connectivity
Influence Measures and Network Centralization
Network Evolution
Formative Assessments:
4 graded quizzes and 8 programming assignments/labs.
ASSESSMENT:
For summative assessments, Coursera will provide question banks for which exams can be
conducted on the Coursera platform or the faculty will create their own assessments.
Note: If a Course or Specialization becomes unavailable prior to the end of the Term, Coursera may replace such
Course or Specialization with a reasonable alternative Course or Specialization.