Artificial Intelligence Syllabus
PYTHON
Introduction:
What is Python and history of Python?
Installing Anaconda, Jupyter Notebook
First Program
Python Identifiers, Keywords and Indentation
Comments
Getting User Input
Python Data Types
What are keywords
What are variables?
Python Inbuilt Functions

Control-Flow Statements:
if-else
Elif
While loop
For loop
Range Function
Break
Assert
Pass
Return
Coding Assignment

Data Structures:
What are Data Structures?
Lists in Python
Code Walkthrough on Lists
Understanding Iterators
Tuple in Python
Code Walkthrough on Tuple
Dictionaries in Python
Code Walkthrough on Dictionaries
Sets in Python
Code Walkthrough on Sets
More examples on Data Structures

Functions:
What are functions in Python?
Defining and Calling Functions
Inbuilt Functions
User Defined Functions
Lambda Function
Split Function
Strip Function
Map Function
Filter Function
Format Function
Code Walkthrough on User Define Functions
Regular Expressions Basics

Object Oriented Programming:
Why do we need Object Oriented Programming?
What is a class?
What is an object?
What is Self?
Constructors
Global and local variables
Static and Dynamic Variables
Abstraction
Inheritance
Encapsulation
Polymorphism
Code Walkthroughs on OOP

Exception Handling and GUI :
Why do we need to handle exceptions?
Errors in Python
Compile-Time Errors
Runtime Errors
What is Exception?
try....except...else
try-finally clause
Raising an exceptions
User Defined Exceptions
Graphical User Interface in python
Tkinter
Button Widget ,Label Widget and Text Widget

Miscellaneous Topics :
SQL connection with Python using SQLITE Library
Multi-Threading and Multi-Processing
Introduction to Web-scraping
Beautiful Soup Library
Numpy Library for Data Analysis
Code Walkthrough On Numpy Library
Pandas Library for Data Analysis
Code Walkthrough On Pandas Library
Matplotlib Library for Data Analysis
Code Walkthrough On Matplotlib Library
Revision Sessions
Assignment Discussions

Project Discussion:
Defining the Business Problem
Constraints
Flow Diagram
Libraries Used
Results and Conclusion
Future Scope
References

SQL
Introduction:
What is SQL?
Why do we need SQL?
What is DataBase Management System?
Types of DBMS
Execution Of SQL query
Difference Between SQL and MYSQL
Introduction to MySQL
Installation of MySQL server
Download sample database
Load sample database to work.

Basic SQL Keywords:
Basic SELECT Statement
Limit/Offset
OrderBy
Distinct
Where
Comparison Operators
Null
Logical Operators
Aggregate Operators(Count, Max, Min, Avg, Sum)
Group By
Having
Order Of Keywords
Wildcard Operators

JOINS:
What are Joins?
Inner Join
Quter Join
Left Join
Right Join
Self Join
SubQueries/NestedQueries/Inner Queries
Triggers
Stored Procedures

DMIL/DDL.
DML.:Insert
DML.:Update, Delete
DDL:Create Table
DDL.:Alter:Add,Drop,Modify
DDL.:Drop Table, Truncate,Delete
DCL:Data Control Language: GRANT,REVOKE

Probability And Statistics
Introduction:
Why do we need to learn Probability and Statistics?
Descriptive Statistics
Central Tendency(Mean/Median/Mode)
Deviation(Standard Deviation/Variance)
Population and Sample
Distributions
Why do we care about Distributions?

Distributions and Various Tests:
What is Random Variable?
Discrete and Continuous Random Variable
Normal Distribution/Gaussian Distribution
PDF and CDF of Gaussian distribution
Uniform Distribution
Q-Q Test
K-S Test
What is Sampling?
Types of Sampling

Inferential Statistics:
Correlation Vs Causation
Hypothesis Testing
Confidence Interval
Permutation Resampling Test
A/B Testing

Case Studies/Project:
Case Study-1
Case Study-2
DataScience-1
Machine Learning

Industry Case Studies:
Case Study-1
Case Study-2
DataScience Vs DataAnalysis Vs MachineLearning Vs DeepLearning
Introduction to Numpy, Pandas, Sci-kit Learn and Matplotlib Library
Importing data from different Sources

Basic Terminologies and Basic Maths:
Traditional Programming Vs Machine Learning
Types of Machine Learning Problems
Supervised and Unsupervised Learning
Classification and Regression
Overfitting and Underfitting
What is a point and a Vector?
Distance between 2 points, Distance between point and a line.
Equation of a line, Equation of a Plane, Equation of a hyper plane.
Dot product and Projection of one vector onto another.
Basics of Differentiation
KNN(K nearest Neighbour) Algorithm
Geometric Intuition of KNN
Mathematical Intuition of KNN
Limitations of KNN
What are Hyper-parameters?
Hyper-parameters Tuning
Why do we need Cross-Validation?
Code Walkthrough on KNN

Supervised Learning Continues:
Naive Bayes algorithm
What is Conditional Probability
What is Naive about Naive Bayes?
Geometric Intuition of Naive Bayes
Mathematical Intuition of Naive Bayes
Limitations of Naive Bayes
Hyperparameter Tuning in Naive Bayes
Code Walkthrough of Naive Bayes
Introduction to Logistic Regression
Geometric Intuition of Logistic Regression
Mathematical Intuition of Logistic Regression
Why do we need sigmoid function?
Regularisation(L1 and L2)
Limitations of Logistic Regression
Code Walkthrough of Logistic Regression

Supervised Learning Continues:
Introduction to Linear Regression
Geometric and Mathematical Intuition
Assumptions of Linear Regression
Limitations of Linear Regression
Code Walkthrough of Linear Regression
Optimisation Theory
Convex and Non Convex Functions
Gradient Descent
Stochastic Gradient Descent
Introduction to SVM(Support Vector Machines)
Geometric Intuition
Mathematical Intuition
Hard and Soft SVM
Kernalisation in SVM(Radial Basis Function)
Limitations of SVM
Code Walkthrough of SVM

Decision Tree and Ensembles :
Decision Tree
Geometric Intuition of Decision Tree
Mathematical Intuition of Decision Tree
Entropy and Gini Impurity
Information Gain
Limitations of Decision Tree
Code Walkthrough of Decision Tree
What is Ensembles
Bagging and Boosting
What is Ensembles?
Bagging and Boosting
Concept of Bootstrapping
Introduction to Random Forest
Variance and Bias
Geometric Intuition of Random Forest
Why Random Forest is so famous?
Code Walkthrough of Random Forest
Performance Metric and Different

Situations in Supervised Learning :
Accuracy
Why Accuracy as a metric will fail in most of the real world cases?
Precision and Recall
F1 Score
Confusion Matrix
Log-loss
ROC-AUC Curve
RMSE(Root Mean Square Error)
R2(Coefficient of Determinant)
MAD(Median Absolute Deviation)
How to Handle Outliers in the data?
How to deal with the imbalance data?
How to handle categorial data?
Scaling of Features
Curse of Dimensionality

Unsupervised Learning and Dimension Reduction:
What is Unsupervised Learning?
What is Clustering?
K-Means Clustering
Hierarchal Clustering
Why Dimensions Reduction?
PCA(Principle Component Analysis)

Machine Learning Project :
Business Problem
Contraints
Data Collection
Formulate Business Problem to Machine Learning Problem
Data Cleaning
Data Preprocessing
EDA(Exploratory Data Analysis)
Modelling
Evaluating the Performance of the models
Retrain if necessary
Deployment
Artificial Intelligence With Deep Learning

History of Neural Networks:
Who invented Neural Network?
What is the intuition of a Neural Network?
What is a perceptron?
Connecting Logistic Regression, Linear Regression with Perceptron
Multi Layer Perceptron
Training of a Perceptron
MLP and Backpropogation)
Notation
Training a MLP:Chain Rule
Training a MLP:Memoization
Back propogation
Activation Functions
Sigmoid
Tanh
RELU
Vanishing gradient

Deep Multi LayerPerceptrons :
Dropout and Regularisation
Batch Normalisation
Batch SGD with Momentum
Adam
Softmax and Cross-Entropy
How to train Deep MLP?
Tensorflow and Keras Overview
Install Tensorflow
Softmax Classifier on MNIST data
Code Walkthrough of MLP
Hyperparameter Tuning in Keras
Introduction to CNN :
Introduction to CNN(Convolution Neural Network)
What is Convolution?
(Convolution:Padding and Strides
Convolution over RGB images
Max Pooling
CNN Training

Introduction to CNN Continues :
AlexNet
VGGNet
Residual Network
Inception Network
What is Transfer Learning?
Code Walkthrough of CNN

Introduction to RNN :
Why RNN(Recurrent Neural Network)?
Training RNN
Types of RNN
Need of LSTM
|. STM(Long Short Term Memory)
Deep RNN
Bidirectional RNN
Code Walkthrough of RNN

Introduction to NLP :
What is NLP(Natural Language Processing)?
BOW(Bag of Words)
Text Preprocessing: Stemming and Lemmatisation
Stop Word Removal
Tokenisation
Unigram, Bigram, Ngrams
TF-IDF
Weighted TF-IDF
Word2Vec(W2V)
Code Walkthrough of NLP Techniques

Deep Learning Project :
Business Problem Contraints
Data Collection
Formulate Business Problem to Deep Learning Problem
Data Cleaning
Data Preprocessing
EDA (Exploratory Data Analysis)
Feature Extraction
Modelling
Evaluating the Performance of the models
Retrain if necessary