b

Post Graduate @bjeigX in

Machine Learning & AI
(Program Curriculum)

Batch starts
Note: This - 31stisMarch,
curriculum 2019
subject to change based on inputs from IIITB and Industry
Prep sessions starts - 20th Jan, 2019
Note: This curriculum is subject to change based on inputs from IIITB and Industry

COURSE MODULE NAME SESSION SESSION NAME

INSTALLATION

BASICS - PRINTING, APPLICATIONS IN DATA ANALYSIS,

DEVELOPMENT, DATA VISUALISATION ETC.

LISTS
DATA STRUCTURES IN PYTHON
TUPLES
DICTIONARIES
SETS
IMPORTING MODULES AND PACKAGES
IF-ELIF-ELSE
LOOPS & CONDITIONAL STATEMENTS
COMPREHENSIONS
INTRODUCTION TO PYTHON CONTROL STRUCTURES & FUNCTIONS
FOR DATA ANALYSIS FUNCTIONS
PREPARATORY CONTENT

EXCEPTION HANDLING
MAP, FILTER & REDUCE
CLASSES AND OBJECTS
BASICS OF OBJECT ORIENTED PROGRAMMING
INHERITANCE
CREATING MODULES
CREATING YOUR OWN MODULES AND PACKAGES CREATING PACKAGES
IMPORTING MODULES AND PACKAGES
INTRODUCING NUMPY
DATA ANALYSIS USING PANDAS INTRODUCING PANDAS
MERGING, SUBSETTING, GROUPING & AGGREGATION

BASICS OF SQL - SELECT, FROM, WHERE

SQL INTRO TO SQL ORDERING, GROUPING, SUBQUERIES, VIEWS
SQL WITH PYTHON (PYMYSQL ETC.)

BASICS OF MATRICES - REVISION

VECTOR SPACES, LINEAR TRANSFORMATIONS, SUBSPACES

LINEAR ALGEBRA
EIGENVALUES AND EIGENVECTORS

INNER PRODUCT SPACES

MATH FOR
DATA ANALYSIS SOLVING A SYSTEM OF LINEAR EQUATIONS IN
N-DIMENSIONS
APPLICATIONS OF LINEAR ALGEBRA
LEAST-SQUARES BEST FIT LINE

FOURIER SERIES EXPANSION

 b

Post Graduate @bjeigX in

Machine Learning & AI
(Program Curriculum)

Batch starts
Note: This - 31stisMarch,
curriculum 2019
subject to change based on inputs from IIITB and Industry
Prep sessions starts - 20th Jan, 2019
Note: This curriculum is subject to change based on inputs from IIITB and Industry

COURSE MODULE NAME SESSION SESSION NAME

GETTING LOCAL DATA

GETTING DATA IN PYTHON DATA FROM SQL

DATA MANIPULATION JSON DATA
IN PYTHON
WIDE & LONG DATAFRAMES (MELT, RESHAPE ETC.)
MANIPULATING DATA IN PYTHON
SLICE, DICE, ORDER, GROUP, AGGREGATE

TYPES OF VISUALISATIONS
INTRODUCTION TO DATA VISUALISATION
INTERPRETING BASIC CHART TYPES
DATA VISUALISATION
IN PYTHON CREATE SCATTER PLOTS, HISTOGRAMS, BAR CHARTS
VISUALISATIONS IN PYTHON USING MATPLOTLIB
FACETS, GRIDS, BOXPLOTS

JARGON BUSTING
INTRODUCTION TO
JARGON BUSTING AND CRISP-DM FRAMEWORK
DATA ANALYSIS FRAMEWORK FOR DATA ANALYSIS

DATA MANIPULATION AND ANALYSIS

INVESTMENT CASE STUDY RECOMMENDING INVESTMENT STRATEGIES TO SPARK FUNDS
(INDIVIDUAL PROJECT)

BASIC PROBABILITY
PROBABILITY, CONDITIONAL PROBABILITY,
CONDITIONAL PROBABILITY
BAYES THEOREM
BAYES THEOREM

RANDOM VARIABLES - DISCRETE AND CONTINUOUS

PDFS AND CDFS

RANDOM VARIABLES, PDFS, CDFS, BINOMIAL
AND NORMAL DISTRIBUTION
INFERENTIAL STATISTICS BINOMIAL DISTRIBUTION
STATISTICS ESSENTIALS

(OPTIONAL)
NORMAL DISTRIBUTION

SAMPLING METHODS

SAMPLING DISTRIBUTIONS AND THE CLT THE CENTRAL LIMIT THEOREM

APPLICATIONS OF CLT

CONFIDENCE INTERVALS
CONFIDENCE INTERVALS, Z-TABLES
Z-TABLES

BASIC PROBABILITY

NULL & ALTERNATE HYPOTHESIS

STANDARDISED SCORE APPROACH

CONCEPTS IN HYPOTHESIS TESTING UNSTANDARDISED TEST SCORE

P-VALUE APPROACH

TYPES OF TESTS

TYPES OF ERRORS

HYPOTHESIS TESTING 1-POPULATION MEAN TEST

2-POPULATION MEAN TEST

SETTING UP HYPOTHESIS TEST
1-POPULATION PROPORTION TEST

2-POPULATION PROPORTION TEST

UNDERSTANDING T-DISTRIBUTION

SETTING UP T-TEST
WHEN NOT TO USE Z-TEST
NON-PARAMETRIC TEST

SETTING UP CHI-SQUARE TEST

SUMMARISING ONE VARIABLE USING MEAN, MEDIAN

MEASURING THE SPREAD - STD DEV, QUARTILE DISTRIBUTION

UNIVARIATE AND SEGMENTED
UNIVARIATE ANALYSIS OUTLIER DETECTION

COMPARISON OF MEANS ACROSS SEGMENTS

EXPLORATORY DATA
BIVARIATE ANALYSIS - CORRELATIONS, CORRELATION MATRICES
ANALYSIS MULTIVARIATE ANALYSIS
ANALYSING MORE THAN TWO VARIABLES AT A TIME

DERIVING NEW METRICS/FEATURES FROM DATES AND TIME

DERIVING NEW VARIABLES
OTHER TYPES OF NEW DERIVATIVE METRICS

GROUP PROJECT EDA PROJECT USE THE CONCEPTS OF EDA TO DECIPHER WHICH TYPES OF
CUSTOMERS DEFAULT ON A LOAN
 b

Post Graduate @bjeigX in

Machine Learning & AI
(Program Curriculum)

Batch starts
Note: This - 31stisMarch,
curriculum 2019
subject to change based on inputs from IIITB and Industry
Prep sessions starts - 20th Jan, 2019
Note: This curriculum is subject to change based on inputs from IIITB and Industry

COURSE MODULE NAME SESSION SESSION NAME

INTRO TO SIMPLE LINEAR REGRESSION

SIMPLE LINEAR REGRESSION
LINEAR REGRESSION IN SKLEARN
LINEAR REGRESSION
INTRO TO MULTIPLE LINEAR REGRESSION
MULTIPLE LINEAR REGRESSION
MULTIPLE LINEAR REGRESSION IN SKLEARN

NAÏVE BAYES WITH 1 FEATURE

CONDITIONAL INDEPENDENCE

NAÏVE BAYES NAÏVE BAYES CLASSIFIER USING NAÏVE BAYES TO MAKE PREDICTIONS

NAÏVE BAYES WITH CONTINUOUS DATA

NAÏVE BAYES IN SKLEARN

SIGMOID FUNCTION

INTRO TO LOGISTIC REGRESSION ESTIMATING & INTERPRETING THE COEFFICIENTS

CHOOSING A PROBABILITY CUTOFF

FEATURE SELECTION THROUGH STEPWISE

LOGISTIC REGRESSION MULTIVARIATE LOGISTIC REGRESSION
FEATURE SELECTION - VIF

C-STATISTIC

MODEL EVALUATION KS STATISTIC & ROC CURVE

THRESHOLD SELECTION

UNSUPERVISED LEARNING
INTRODUCTION TO CLUSTERING
CUSTOMER SEGMENTATION - APPLICATION OF CLUSTERING

STEPS OF THE ALGORITHM

K-MEANS CLUSTERING - ALGORITHM VISUALISING THE K MEANS ALGORITHM

PRACTICAL CONSIDERATIONS IN K MEANS

DATA PREPARATION

MAKING THE CLUSTERS

K MEANS IN SKLEARN
DECIDING THE OPTIMAL K

INTERPRETING THE RESULTS

CLUSTERING AND
STEPS OF THE ALGORITHM
DIMENSIONALITY REDUCTION
MACHINE LEARNING

HIERARCHICAL CLUSTERING - ALGORITHM INTERPRETING THE DENDROGRAM

TYPES OF LINKAGES

CONSTRUCTING THE DENDROGRAM

HIERARCHICAL CLUSTERING IN SKLEARN CUTTING THE DENDROGRAM

INTERPRETING THE DENDROGRAM

THE NEED FOR DIMENSIONALITY REDUCTION

CREATING AND INTERPRETING PRINCIPAL COMPONENTS

DIMENSIONALITY REDUCTION USING PCA
CREATING CLUSTERS USING PRINCIPAL COMPONENTS

IMPLEMENTING PCA IN PYTHON

WHY USE SVM

CONCEPTS OF HYPERPLANES

HYPERPLANES AND SVMS MAXIMUM MARGIN CLASSIFIER

SUPPORT VECTOR MACHINES SUPPORT VECTOR CLASSIFIER

SVM IN SKLEARN

TRANSFORMING NON-LINEAR BOUNDARIES TO LINEAR

KERNELS
THE KERNEL TRICK AND KERNEL FUNCTIONS

CONCEPT OF DECISION TREES

INTERPRETING A DECISION TREE

INTRO TO DECISION TREES ADVANTAGES & DISADVANTAGES

DECISION TREE IN SKLEARN

REGRESSION WITH DECISION TREE

CONCEPT OF HOMOGENEITY

DECISION TREES GINI INDEX

ALGORITHMS FOR DECISION
ENTROPY & INFORMATION GAIN
TREE CONSTRUCTION
MULTISTAGE PROPERTY & GAIN RATIO

SPLITTING BY VARIANCE

TREE TRUNCATION

TRUNCATION & PRUNING TREE PRUNING

COST CONSIDERATION & MISSING DATA

WHY ENSEMBLES WORK

CREATING AN ENSEMBLE - BAGGING AND RANDOM FORESTS

ENSEMBLES BAGGING & BOOSTING
CREATING AN ENSEMBLE - GRADIENT BOOSTING

ENSEMBLES IN SKLEARN

SOLVE THE MOST CRUCIAL BUSINESS PROBLEM FOR A

GROUP PROJECT TELECOM CHURN PROJECT
LEADING TELECOM OPERATOR IN INDIA AND SOUTHEAST ASIA
- PREDICTING CUSTOMER CHURN
 b

Post Graduate @bjeigX in

Machine Learning & AI
(Program Curriculum)

Batch starts
Note: This - 31stisMarch,
curriculum 2019
subject to change based on inputs from IIITB and Industry
Prep sessions starts - 20th Jan, 2019
Note: This curriculum is subject to change based on inputs from IIITB and Industry

COURSE MODULE NAME SESSION SESSION NAME

TERM DISTRIBUTION AND RELEVANCE MODELS,

BAG-OF-WORDS DOCUMENT MODEL, FREQUENCY,
AGGREGATE FUNCTIONS ON WORDS ETC.
DISTRIBUTIONAL HYPOTHESIS
INTRODUCTION TO NLTK - ACCESSING TEXT CORPORA
AND LEXICAL RESOURCES
GETTING STARTED WITH
FREQUENCY AND CONDITIONAL FREQUENCY DISTRIBUTIONS
NLTK, BASICS OF TEXT PROCESSING
ACCESSING TEXT FROM WEB APIS, RSS FEEDS IN
HTML, XML, JSON FORMATS ETC.
ACCESSING AND PROCESSING RAW TEXT
PROCESSING UNICODE TEXTS

REGULAR EXPRESSIONS
NATURAL LANGUAGE PROCESSING

APPLICATIONS OF CLT

USING A TAGGER

MAPPING WORDS TO PROPERTIES USING

PYTHON DICTIONARIES
KEY PHRASE MANAGEMENT
AUTOMATIC TAGGING, N-GRAM TAGGING

LEXICAL PROCESSING PHRASE DETECTION ALGORITHMS

DETERMINING CATEGORY OF A WORD

APPLYING SUPERVISED CLASSIFICATION TO CLASSIFY

TEXT - DECISION TREES, BAYESIAN CLASSIFIERS ETC.
DOCUMENT MODELS
MODELING LINGUISTIC PATTERNS

CHUNKING: DEVELOPING AND EVALUATING CHUNKERS

SENTIMENT ANALYSIS
SEMANTIC TAGGING
TOPIC MODELS

SYNTAX AND SEMANTICS NAMED ENTITY RECOGNITION

UNDERSTANDING ENGLISH GRAMMAR

SYNTAX PARSING, DEPENDENCY GRAMMAR

EXTRACTING FEATURES

MISCELLANEOUS DOCUMENT CLUSTERING APPLICATION OF CLUSTER ANALYSIS IN TEXT DOCUMENTS

TRAINING A CHAT BOT ENGINE

PROJECT BUILDING CHATBOTS WITH RASA
BUILDING A CHAT BOT

INSPIRATION FROM HUMAN BRAIN

INFORMATION FLOW IN A STRUCTURE OF NEURAL NETWORKS WORKING OF A NEURON

NEURAL NETWORK HYPER PARAMETERS OF NEURAL NETWORKS - WEIGHTS,
BIASES AND ACTIVATION FUNCTION

FEEDFORWARD INFORMATION FLOW IN NEURAL NETWORKS

NEURAL NETWORKS AND DEEP LEARNING

DEFINING THE COST FUNCTION

TRAINING A NEURAL NETWORK -
BACKPROPAGATION CALCULATING GRADIENT OF COST

UPDATING THE WEIGHT & BIASES

TRAINING A NEURAL NETWORK
STOCHASTIC GRADIENT DESCENT

OPTIMISATION STRATEGIES IN EXPLORATION & EXPLOITATION

NEURAL NETWORKS
IMPLEMENTING A NEURAL NETWORK ON
MNIST DATA IN PYTHON

CONVOLUTIONAL NEURAL NETWORKS - EXAMPLES OF

IMAGE CLASSIFICATION
CONVOLUTIONAL NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS
ARCHITECTURE OF COMPLEX NEURAL NETWORKS -
SOFTMAX LAYERS, MAXPOOL ETC.

LSTMS
RECURRENT NEURAL NETWORKS RECURRENT NEURAL NETWORKS
IMPLEMENTATIONS OF RNNS ON TEXT DATA (EXAMPLES)

WORKING WITH TENSORFLOW AND KERAS

IMPLEMENTING NEURAL NETWORKS USING
KERAS AND TENSORFLOW USING PREBUILT NETWORKS TO CLASSIFY IMAGES -
CREATING AND DEPLOYING
ALEXNET, GOOGLENET, LENET
NETWORKS USING TENSORFLOW
AND KERAS
USING APIS
MODEL DEPLOYMENT
DEPLOYING AN IMAGE CLASSIFIER

IN THIS MODULE, YOU WILL CREATE A MODEL THAT IDENTIFIES

NEURAL NETWORKS PROJECT GESTURE RECOGNITION
THE GESTURES WITH CONSIDERABLE ACCURACY
 b

Post Graduate @bjeigX in

Machine Learning & AI
(Mli`lXg Curriculum)

Batch starts
Note: This - 31stisMarch,
curriculum 2019
subject to change based on inputs from IIITB and Industry
Prep sessions starts - 20th Jan, 2019
Note: This curriculum is subject to change based on inputs from IIITB and Industry

COURSE MODULE NAME SESSION SESSION NAME

BAYESIAN VERSUS FREQUENTIST ANALYSIS

INTRODUCTION TO CONCEPTS IN BAYESIAN INFERENCE: POSTERIOR, PRIOR, CONJUGACY, MAP, MODEL AVERAGING
BAYESIAN METHODS
EXAMPLES
GRAPHICAL MODELS

STRUCTURE LEARNING, PARAMETER LEARNING, INFERENCE

MARKOV PROPERTIES
PRIMER ON GRAPHICAL MODELS
FACTOR GRAPHS

BAYESIAN BELIEF NETWORKS

SUPERVISED BBN LEARNING - MAXIMUM LIKELIHOOD, PARAMETER LEARNING, OVERVIEW OF STRUCTURED LEARNING

OVERVIEW OF INFERENCE IN BBNS - PEARL'S ALGORITHM, JUNCTION TREE ALGORITHM

LEARNING AND INFERENCE
IN GRAPHICAL MODELS UNSUPERVISED LEARNING IN GRAPHICAL MODELS - MRFS

PROJECT RESTRICTED BOLTZMANN MACHINE ASSIGNMENT

PROBLEMS IN REINFORCEMENT LEARNING

REINFORCEMENT LEARNING

INTRODUCTION TO
REINFORCEMENT LEARNING, MULTIARMED BANDITS
FINITE MDPS
CONCEPTS IN RL: MDPS, AGENT, ENVIRONMENT, GOALS, REWARDS, VALUE FUNCTIONS, POLICY

DYNAMIC PROGRAMMING

EXACT METHODS MONTE CARLO METHODS

TEMPORAL DIFFERENCE LEARNING

APPROXIMATE METHODS POLICY GRADIENT METHODS

REINFORCEMENT LEARNING PROJECT TRAIN AN RL AGENT TO INCREASE THE REVENUE OF A CAB-SERVICE COMPANY BY OPTIMIZING CAB DRIVER'S STRATEGIES