BIRLA INSTITUTE OF TECHNOLOGY & SCIENCE, PILANI

WORK INTEGRATED LEARNING PROGRAMMES

Digital Learning

Part A: Content Design

Course Title Applied Machine Learning
Course No(s) ZG568
Credit Units 4
Course Authors Sugata Ghosal
Version No 1.0
Date Jan 05, 2021

Course Objectives

Machine learning is a rapidly growing field at the intersection of computer science and statistics. It is
responsible for tremendous advances in technology, from personalized product recommendations to
speech recognition in cell phones. The goal of this course is to provide a broad introduction to the key
ideas in machine learning. The emphasis will be on intuition and realistic examples rather than
theoretical results, though experience with statistics, calculus and linear algebra will be assumed.
Through a variety of lecture examples and programming projects, students will learn how to apply
powerful machine learning techniques to realistic problems, run evaluations and interpret results, and
understand limitations.

No Course Objective

CO1 Provide a broad background to the key concepts and techniques in machine learning

CO2 Hands on learning to apply contemporary machine learning techniques on realistic

problems

CO3 Evaluation and interpretation of results

CO4 Understand limitations of different machine learning techniques

CO5 Gain experience in working with machine learning software pipeline

Text Book(s)

T1 Aurelien Geron, “Hands-On Machine Learning with Scikit-Learn, Keras and

Tensorflow”, O’Reilly, 2020
T2 P-N Tan, M. Steinbach, Vipin Kumar, “Introduction to Data Mining”, 2016, Pearson

Reference Book(s) & other resources

R1 Christoph Molner, “Interpretable Machine Learning”, 2020,

https://christophm.github.io/interpretable-ml-book/
R2 Pedro Domingos, “A Few Useful Things to Know About Machine Learning”, pp. 78-87,
Communications of the ACM, vol. 55 no. 10, October 2012.
Modular Content Structure

No Title of the Module References

M1 Introduction to Machine Learning T1: Chapter 1
1.1. What and Why R2
1.2. Applications of Machine Learning
1.3. Types of Machine Learning
1.4. Challenges in Machine Learning

M2 Big Picture: End-to-end Machine Learning T1: Chapter 2

2.1. Framing the ML Problem T2: Chapter 2-3
2.2. Data Types, Pre-processing, Visualization and
Analysis

M3 Big Picture: End-to-end Machine Learning T1: Chapter 2-3

3.1 Model Selection and Training T2: Chapter 4
3.1.1. Prediction Problem
3.1.2. Classification Problem
3.2 Evaluation
3.2.1. Prediction Problem
3.2.2. Classification Problem
3.3 Machine Learning Pipeline

M4 Linear Prediction Models T1: Chapter 4

4.1. Linear Regression T2: Appendix D
4.2. Gradient Descent and Variants
4.3. Regularization
4.4. Bias Vs. Variance
M5 Classification Models I T1: Chapter 4, 5
5.1. Naïve Bayes T2: Chapter 5
5.2. Logistic Regression
5.3. Support Vector Machines
5.4. Comparative Analysis
M6 Classification Models II T1: Chapter 6-7
6.1. Decision Tree T2: Chapter 4, 5
6.2. Challenges with Decision tree
6.3. Ensembles
6.2.1. Bagging
6.2.2. Boosting
6.4. Random Forest
M7 Unsupervised Learning T1: Chapter 8-9
7.1. Dimensionality reduction T2: Chapter 8-9
7.2 K-means Clustering
7.4 Gaussian Mixture Model
M8 Neural Networks T1: Chapter 10-11
8.1. Perceptrons and Delta Rule T2: Chapter 5
8.2. Multi-Layer Perceptrons and Backpropagation
8.3. Deep Learning
M9 Deep Networks T1: Chapter 14, 15
9.1. Convolutional Neural Network
9.2. Recurrent Neural Network
9.3. Applications in Image and Text Processing
M10 FAccT Machine Learning R1
10.1. Bias and Fairness
10.2. Interpretability and Transparency

Learning Outcomes:
No Learning Outcomes

LO1 High-level conceptual understanding of machine learning field and its applicability
and limitations

LO2 Ability to frame a machine learning problem and select candidate machine learning
models

LO3 Ability to design and implement an end-to-end machine learning based solution using
Python and appropriate libraries and do trouble shooting

LO4 Ability to evaluate and interpret the results from a machine learning system

Part B: Learning Plan

Academic Term 2023-24 Semester 1

Course Title Applied Machine Learning

Course No ZG564

Lead Instructor Dr. Anita Ramachandran

Session Study / HW
No. Topic Title Resource
Reference

Introduction to Machine Learning: What and Why, Applications of T1: Chapter 1

1 Machine Learning, Types of Machine Learning, Challenges in Machine R2
Learning

T1: Chapter 2
2 End-to-end Machine Learning: Framing the ML Problem. Data Types,
T2: Chapter 2-3
Pre-processing, Visualization and Analysis

T1: Chapter 2-3

3 End-to-end Machine Learning: Model Selection and Training for
T2: Chapter 2-3
Prediction and Classification, Evaluation, Machine Learning Pipeline.

Linear Prediction Models: Linear Regression, Gradient Descent and T1: Chapter 4
4
Variants, Regularization, Bias Vs. Variance
 Classification Models I: Naïve Bayes classification, Applications in text T2: Chapter 5
5 and image classification

Classification Models I: Logistic Regression, Log Loss error function, T1: Chapter 4
6 Optimization using gradient descent, Feature transformation for
nonlinear classification

Classification Models I: Support Vector Machine. Margin maximization. T1: Chapter 5

7 Non-linear SVM. Kernel Function. T2: Chapter 5

8 Review of Session 1 to 7

Classification Models II: Decision Tree. Entropy and information gain. T1: Chapter 6
9 Construction algorithm. Challenges with Decision Tree T2: Chapter 4

Classification Models II: Ensembles techniques. Bagging, boosting, T1: Chapter 7

10 Random Forest T2: Chapter 5

Unsupervised Machine Learning: Dimensionality reduction and feature T1: Chapter 8-9
11 extraction, K-means clustering, Gaussian Mixture Model T2: Chapter 8

12 Artificial Neural Networks: Perceptions, Delta rule, Design for Boolean

logic gates and linear classification, Neural networks, Design for T1: Chapter 10
nonlinear classification and Boolean functions, Backpropagation T2: Chapter 5
algorithm

13. Artificial Neural Networks: Deep Learning, Characteristics, Error

T1: Chapter 11
Surface, hyperparameters, Regularization, Weight Updates.

14. Deep Networks: Convolutional Neural Networks, The Convolution

T1: Chapter
Operation, Pooling, padding, architectures for classification. 14-15
Recurrent Neural Networks, Architecture, training, bidirectional network,
long short-term memory, deep recurrent network. Sequence processing.

FAccT Machine Learning. Bias and Fairness, Interpretability and

15 R1, Slides
Transparency

16 Books, Slides,
Review of session 9 to 15
Web references
Evaluation Scheme:
Legend: EC = Evaluation Component; AN = After Noon Session; FN = Fore Noon Session
No Name Type Duration Weight Day, Date, Session, Time
EC-1 Assignment Offline - 30% TBA
EC-2 Mid-Semester Closed 1.5 hours 30% TBA
Test Book
EC-3 Comprehensive Open 2.5 hours 40% TBA
Exam Book

Important Information:
Syllabus for Mid-Semester Test (Closed Book): Topics in CS 1-8.
Syllabus for Comprehensive Exam (Open Book): All topics given in plan of study

Evaluation Guidelines:

1. For Closed Book tests: No books or reference material of any kind will be permitted.
Laptops/Mobiles of any kind are not allowed. Exchange of any material is not allowed.
2. For Open Book exams: Use of prescribed and reference text books, in original (not
photocopies) is permitted. Class notes/slides as reference material in filed or bound form is
permitted. However, loose sheets of paper will not be allowed. Use of calculators is permitted
in all exams. Laptops/Mobiles of any kind are not allowed. Exchange of any material is not
allowed.
3. If a student is unable to appear for the Regular Test/Exam due to genuine exigencies, the
student should follow the procedure to apply for the Make-Up Test/Exam. The genuineness of
the reason for absence in the Regular Exam shall be assessed prior to giving permission to
appear for the Make-up Exam. Make-Up Test/Exam will be conducted only at selected exam
centres on the dates to be announced later.
It shall be the responsibility of the individual student to be regular in maintaining the self-study
schedule as given in the course handout, attend the lectures, and take all the prescribed evaluation
components such as Assignment/Quiz, Mid-Semester Test and Comprehensive Exam according to the
evaluation scheme provided in the handout.