AI Using

Python
Python Duration: 6 Months
Introduction To Python
l Why Python
l Application areas of python
l Python implementations
l Cpython

l Jython

l Ironpython

l Pypy

l Python versions
l Installing python
l Python interpreter architecture
l Python byte code compiler

l Python virtual machine(pvm)

Writing and Executing First Python Program

l Using interactive mode
l Using script mode
l General text editor and command window

l Idle editor and idle shell

l Understanding print() function

l How to compile python program explicitly
Python Language Fundamentals
l Character set
l Keywords
l Comments
l Variables
l Literals
l Operators
l Reading input from console
l Parsing string to int, float
Python Conditional Statements
l If statement
l If else statement
l If elif statement
l If elif else statement
l Nested if statement
Looping Statements
l While loop
l For loop
l Nested loops
l Pass, break and continue keywords
Standard Data Types
l Int, float, complex, bool, nonetype
l Str, list, tuple, range
l Dict, set, frozenset

l
String Handling
l What is string
l String representations
l Unicode string
l String functions, methods
l String indexing and slicing
l String formatting

Python List
l Creating and accessing lists
l Indexing and slicing lists
l List methods
l Nested lists
l List comprehension
Python Tuple
l Creating tuple
l Accessing tuple
l Immutability of tuple
Python Set
l How to create a set
l Iteration over sets
l Python set methods
l Python frozenset

Python Dictionary
l Creating a dictionary
l Dictionary methods
l Accessing values from dictionary
l Updating dictionary
l Iterating dictionary
l Dictionary comprehension
Python Functions
l Defining a function
l Calling a function
l Types of functions
l Function arguments
l Positional arguments, keyword arguments

l Default arguments, non-default arguments

l Arbitrary arguments, keyword arbitrary arguments

l Function return statement

l Nested function
l Function as argument
l Function as return statement
l Decorator function
l Closure
l Map(), filter(), reduce(), any() functions
l Anonymous or lambda function
Modules & Packages
l Why modules
l Script v/s module
l Importing module
l Standard v/s third party modules
l Why packages
l Understanding pip utility
File I/O
l Introduction to file handling
l File modes
l Functions and methods related to file handling
l Understanding with block
Regular Expressions(Regex)
l Need of regular expressions
l Re module
l Functions /methods related to regex
l Meta characters & special sequences

Object Oriented Programming

l Procedural v/s Object Oriented Programming
l OOP Principles
l Defining a Class & Object Creation
l Inheritance
l Encapsulation
l Polymorphism
l Abstraction
l Garbage Collection
l Iterator & Generator
Exception Handling
l Difference Between Syntax Errors and Exceptions
l Keywords used in Exception Handling
l try , except , finally , raise , assert

l Types of Except Blocks

l User-defined Exceptions

GUI Programming
l Introduction to Tkinter Programming
l Tkinter Widgets
l Layout Managers
l Event handling
l Displaying image
Multi-Threading Programming
l Multi-processing v/s Multi-threading
l Need of threads
l Creating child threads
l Functions /methods related to threads
l Thread synchronization and locking

SQL Using MySQL

Introduction to RDBMS
l What is Relational Database Package
l Difference between SQL & Database
l Installing MySQL Server database

SQL Basic
l DDL: Create, Alter, Drop, etc.
l DML: Insert, Update, Delete ,etc.
l DQL : Select
l Autoincrement field
l SQL Comments
l SQL Aliases
Savepoint & rollback
SQL Constraints
Not NULL, Unique key
Primary key, Check
Default, Foreign key
SQL Operators
Arithmetic operators
Logical operators
Conditional operators
Like, between, in operators
SQL Clauses
Order by
Where
Limit/top
Group by
having
SQL Joins
Inner Join
Left Join
Right Join
Full Join
SQL View
creating view
updating view
fetching data from view
SQL Functions
String functions
Aggregate functions
Date & time functions
Stored Procedures & Functions
Understanding stored procedures and their key benefits
Working with stored procedures
Studying user-defined functions
Working with CSV Files:
How to write result to csv file
How to read csv file
Python Database Connectivity
Database Drivers and connectors
Creating connection object
Understanding cursor object
Executing SQL statements using cursor
Fetching records from cursor
Storing and retrieving Date and Time

MONGODB
Introduction To MongoDB
Understanding NoSQL DB
NoSQL vs. SQL DB
Understanding Mongo DB
Downloading & Installation
Introduction of MongoDB shell and Compass
Understanding database, collection & document
Crud Operations
Insert Document
Delete Document
 Update Document
Query Document
Operators In MongoDB
Query and Projection operators
Update operator
Aggregation Pipeline operators
Methods In MongoDB
limit and sort
bulk methods
other methods
Indexing And Relationships
Types of Indexes
Creating an Indexes
Dropping an Indexes
Defining Relationships between Documents
Python Connectivity With MongoDB
Introduction to pymongo
Installing pymongo module
MongoClient
Getting database and collection
CRUD operations
Range Queries

Statistics & Analytics

Introduction to Statistics
Sample or population
Measures of central tendency
l Arithmetic mean

l Harmonic mean

l
Geometric mean
l Mode

l Quartile
l
First quartile
l
Second quartile(median)
l
Third quartile
l Standard deviation

Probability Distributions
l Introduction to probability
l Conditional probability
l Normal distribution
l Uniform distribution
l Exponential distribution
l Right & left skewed distribution
l Random distribution
l Central limit theorem
l

Hypothesis Testing
l

l Normality test
l Mean test
l T-test

l Z-test

l
ANOVA test
l Chi square test
l Correlation and covariance
Numpy Package
l Difference between list and numpy array
l Vector and matrix operations
l Array indexing and slicing
Pandas Package
Introduction to pandas
l Labeled and structured data
l Series and dataframe objects
How to load datasets
l From excel
l From csv
l From html table
Accessing data from Data Frame
l at & iat
l loc & iloc
l head() & tail()
Exploratory Data Analysis (EDA)
l describe()
l groupby()
l crosstab()
l boolean slicing / query()
Data Manipulation & Cleaning
l Map(), apply()
l Combining data frames
l Adding/removing rows & columns
l Sorting data
l Handling missing values
l Handling duplicacy
l Handling data error
Handling Date and Time
Data Visualization using matplotlib and seaborn packages
l Scatter plot, lineplot, bar plot
l Histogram, pie chart,
l Jointplot, pairplot, heatmap
l Outlier detection using boxplot

Machine Learning
Introduction To Machine Learning
l Traditional v/s Machine Learning Programming
l Real life examples based on ML
l Steps of ML Programming
l Data Preprocessing revised
l Terminology related to ML
Supervised Learning
l Classification
l Regression
Unsupervised Learning
l Clustering
KNN Classification
l Math behind KNN
l KNN implementation
l Understanding hyper parameters
Performance metrics
l Math behind KNN
l KNN implementation
l Understanding hyper parameters
Regression
l Math behind regression
l Simple linear regression
l Multiple linear regression

l
 l Polynomial regression
l Boston price prediction
l Cost or loss functions
l Mean absolute error

l Mean squared error

l Root mean squared error

l
Least square error
l Regularization
Logistic Regression for classification
l Theory of logistic regression
l Binary and multiclass classification
l Implementing titanic dataset
l Implementing iris dataset
l Sigmoid and softmax functions

Support Vector Machines

l Theory of SVM
l SVM Implementation
l kernel, gamma, alpha
Decision Tree Classification
l Theory of decision tree
l Node splitting
l Implementation with iris dataset
l Visualizing tree
Ensemble Learning
l Random forest
l Bagging and boosting
l Voting classifier
Model Selection Techniques
l Cross validation
l Grid and random search for hyper parameter tuning
Recommendation System
l Content based technique
l Collaborative filtering technique
l Evaluating similarity based on correlation
l Classification-based recommendations
Clustering
l K-means clustering
l Hierarchical clustering
l Elbow technique
l Silhouette coefficient
l Dendogram
Text Analysis
l Install nltk
l Tokenize words
l Tokenizing sentences
l Stop words customization
l Stemming and lemmatization
l Feature extraction
l Sentiment analysis
l CountVectorizer
l TfidfVectorizer
l Naive bayes algorithms
Dimensionality Reduction
l Principal component analysis(PCA)

Open CV
l Reading images
l Understanding gray scale image
l Resizing image
l
 l Understanding haar classifiers
l Face, eyes classification
l How to use webcam in open cv
l Building image data set
l Capturing video
l Face classification in video
l Creating model for gender prediction

Deep Learning & Neural Networks

Introduction To Artificial Neural Network
l What is artificial neural network (ANN)?
l How neural network works?
l Perceptron
l Multilayer perceptron
l Feedforward
l Back propagation
Introduction To Deep Learning
l What is deep learning?
l Deep learning packages
l Deep learning applications
l Building deep learning environment
l Installing tensor flow locally

l Understanding google colab

Tensor Flow Basics

l What is tensorflow?
l Tensorflow 1.x v/s tensorflow 2.x
l Variables, constants
l Scalar, vector, matrix
l Operations using tensorflow
l Difference between tensorflow and numpy operations
l Computational graph
Optimizers
l What does optimizers do?
l Gradient descent (full batch and min batch)
l Stochastic gradient descent
l Learning rate , epoch
Activation Functions
l What does activation functions do?
l Sigmoid function,
l Hyperbolic tangent function (tanh)
l ReLU –rectified linear unit
l Softmax function
l Vanishing gradient problem
Building Artificial Neural Network
l Using scikit implementation
l Using tensorflow
l Understanding mnist dataset
l Initializing weights and biases
l Gradient tape
l Defining loss/cost function
l Train the neural network
l Minimizing the loss by adjusting weights and biases
Modern Deep Learning Optimizers and Regularization
l SGD with momentum
l RMSprop
l AdaGrad
l Adam
l Dropout layers and regularization
l Batch normalization
l
Building Deep Neural Network Using Keras
l What is keras?
l Keras fundamental for deep learning
l Keras sequential model and functional api
l Solve a linear regression and classification problem with example
l Saving and loading a keras model

Convolutional Neural Networks (CNNs)

l Introduction to CNN
l CNN architecture
l Convolutional operations
l Pooling, stride and padding operations
l Data augmentation
l Building,training and evaluating first CNN model
l Model performance optimization
l Auto encoders for CNN
l Transfer learning and object detection using pre-trained CNN models
l LeNet

l AlexNet

l VGG16

l ResNet50

l Yolo algorithm

Word Embedding
l What is word embedding?
l Word2vec embedding
l CBOW

l Skipgram

l Keras embedding layers

l Visualize word embedding
l Google word2vec embedding
l Glove embedding
Recurrent Neural Networks (RNNs)
l Introduction to RNN
l RNN architecture
l Implementing basic RNN in tensorflow
l Need for LSTM and GRU
l Deep RNN/LSTM/GRU
l Text classification using LSTM
l Prediction for time series problem
l Seq-2-seq modeling
l Encoder-decoder model

Generative Adversarial Networks (GANs)

l Introduction to GAN
l Generator
l Discriminator
l Types of GAN
l Implementing GAN using neural network
Speech Recognition APIs
l Text to speech
l Speech to text
l Automate task using voice
l Voice search on web
Projects(Any Four)
l Stock Price Prediction Using LSTM
l Object Detection
l Attendance System Using Face Recognition
l Facial Expression and Age Prediction
l Neural Machine Translation
l Hand Written Digits& Letters Prediction

l
l Number Plate Recognition
l Gender Classification
l My Assistant for Desktop
l Cat v/s Dog Image Classification

2.0 NOIDA SEC-63

H-43 Sector-63
Noida-201301

+91 7042175774
+91 9810851363