Python with Artificial Intelligence (AI) Training

• Introduction to markdown

• Using Python as calculator

• Number data type
• Taking input from the users
• Type casting and type checking
• Type validation
• Number type with conditionals

• Modulus operator
• Boolean expressions
• Logical operators
• Conditional execution
• Chained conditionals
• Nested conditionals
• Recursion
• Stack diagrams for recursive functions
• Infinite recursion

• Multiple assignments
• Updating variables
• The while statement
• Break
• Debugging
• For loop

• Introduction
• Single line vs multiline string
• Indexing
• slicing
• len()
• Loop: for loop using range()
• Loop with conditionals
• continue vs break
• characters vs substrings
• Immutable data type
• String methods: .replace(),.lower(), .upper(),.title() .lstrip(), .rstrip(), .strip(), .split(), .join(), .isdigit(), isupper(), islower(), .format()

      List

• Introduction to list
• Indexing/Negative indexing
• Slicing
• looping & conditionals, len()
  • Different types of for loop ,while loop, for loop vs while loop
• list of list and nested loop
• Membership operators: in , not in
• Mutable vs Immutable data type with exmaple
• List methods: .insert(), .append(), .remove(), .pop(), .sort(), .extend(), .remove(), .sort()
• List Comprehension
• with if and else

Tuple

• Introduction to tuple
• Indexing , slicing, looping
• list vs tuple
• Typecasting list -> tuple and tuple ->list
• tuple unpacking

Set

• Introduction to set
• .remove() , .add(), .discard() in sets
• Type conversion
• Set operation in Python : union, intersection, difference
• Frozenset vs set

Dictionary

• Introduction
• disctionary methods: .get(), .update(), .keys(), .values(), .pop()
• Loop and dictionary comprehension
• Nested Dictionary

• Identity Operators

• Introduction and syntax: Why function is necessary
• Function definition and function call
• arguments/parameters in function
• return statement in function
• returning multiple value from function
• Handling multiple return values
• Default argument vs non default argument and why it is necessary
• global and local variables
• *args vs **kwargs
• Introduction to Recursion and Recursion tree
• pass keyword

• Class and Objects
• Class attribute and Object attribute
• Initilizing object attribute
• __init__()
• Self keyword and its importance
• Inheritance and its types
• Single Inheritance
• super() method
• Mulitple Inheritance
• Multi-level Inheritance
• Abstraction and Access specifiers
• Polymorphism
• + and len()
• Operator overloading using Dunders/magic method (user defined class)
• function overriding
• Encapsulation

• Understanding exceptions in Python
• Types of exceptions and their meaning
• Importance of exception handling
• Handling Exceptions
  • Using try-except blocks to handle exceptions
  • Catching specific exceptions
  • Handling multiple exceptions
  • Using the finally clauses
• Raising Exceptions

• open()
• modes:
  • read : ‘r’
    • read(), readline(), readlines()
  • write: ‘w’
  • append: ‘a’
  • create: ‘x’
  • Comparison of append and write modes
• File handling on CSV files.
• DictReader and DictWriter
• File handling with exception handling

• Lambda function/Annynomous Function:
  • map() , filter()
• os library
• random library
• math library

• Creating database
• Defining table structure with SQL statements and Specifying column names, data types, and constraints
• Inserting new records into tables using SQL INSERT statements
• Retrieving data from tables using SQL SELECT statements
• Modifying existing data in tables using SQL UPDATE statements
• Removing tables data  using SQL DELETE statements
• Filtering data using the WHERE clause in SQL SELECT statements

• Installing Git Bash
  • Overview of Git Bash
  • Installation
• Creating a GitHub Account
  • Sign up for a GitHub account
  • Set up profile
• Creating an Empty Repository
  • Create a new empty repository on GitHub
• Initializing a Git Repository Locally
  • Initialize a Git repository on your local machine using Git Bash
• Tracking Files
  • Add files to the staging area
  • Commit changes to the repository
• Configuration of Global User Information
  • Configure your global user.name and user.email for Git
• Branching (main)
  • Understand the concept of branches
  • Work with the default main branch
• Adding a Remote
  • Connect your local repository to the remote repository on GitHub
  • Configure the remote repository URL
• Pushing Changes
  • Push your local changes to the remote repository on GitHub
• Cloning
  • Clone a repository from GitHub to your local machine using Git Bash
• Creating a New Branch
  • Create a new branch for making changes
  • Switch between branches
• Pushing Changes to a Branch
  • Push your changes to the remote repository on a specific branch

• Introduction to Pandas
• DataFrame Data Structure
• Reading and writing csv files using DataFrame
• Manipulating DataFrame

• Introduction to Matplotlib and Seaborn and plotly
• Basic plotting using any of these library

• Web Scraping project + Databse
  OR
• Any desktop application: eg. Data Entry application

• Introduction
• Supervised vs. Unsupervised Learning
• Installing Anaconda and Managing Environment
• Familiarization with Datasets
• Numpy
• Scikit Learn
• Matplotlib
• Pandas

• Importing the Dataset
• DataFrame Data Structure
• Missing Data
• Querying a DataFrame
• Manipulating DataFrame
• Splitting the Dataset into the Training set and Test set
• Feature Scaling

• Gradient descent
• Correlation Analysis and Feature Selection
• Observe Model Performance
• Multiple Regression and Feature Importance
• Cross validation
• Linear regression implementation

• Cross validation
• Confusion Matrix, Precision, Recall and F1 Score
• Precision and Recall Tradeoff
• The ROC Curve

• Introduction
• Classification using SVM
• Support Vector Regression

• Introduction
• Lazy learning
• Euclidean-distance
• Implementation of K-nearest neighbor

• Introduction
• Implementation of Naive Bayes
• Classification applications

• Introduction
• Entropy
• Implementation

• Overview of Time Series Modeling
• Time Series Pattern
• White Noise
• Stationarity
• Removal of Non-Stationarity
• Steps in Time Series Forecasting
• Examples

• Overview of Text Mining
• Applications of Text Mining
• Natural Language Toolkit Library
• Text Extraction and Preprocessing
• Tokenization
• N-grams
• Stop Word Removal
• Stemming
• Lemmatization
• POS Tagging
• Named Entity Recognition

• Introduction to Flask
• URL and App routing
• Streamlit application – ML Model Deployment

• Introduction
• Purposes of Recommender Systems
• Collaborative Filtering
• Content based Filtering
• Hybrid Recommender System
• User-Movie Recommendation Model
• Movie-Movie recommendation

• Introduction to Google co-lab and Anaconda
• Numpy
• Pandas
• Plotting and Charting

• Matrix
• Calculus
• Linear Algebra
• Probability and Statistics

• Tensorflow
• Pytorch
• Keras
• Theano

• Computer Vision Overview
• Image Formation
• History
• Image Processing and Feature Detection
• Introduction to Open CV
• Different Types of Filter
• Feature Detection
• Edge Detection
• Haar-like Features
• Frequency Domain Analysis

• History
• Why Deep Learning Taking Off
• Building Block of deep Learning
• Application of Deep Learning

• Multilayer Perceptron
• Back Propagation
• Working Of neural network
• Adjusting the weights
• Gradient Descent
• Stochastic Gradient Descent

• Foundations of Convolutional Neural Network
• CNN Architecture
• Convolution Operation
• ReLU Layer
• Pooling
• Flattening
• Full Connection
• Softmax & Cross-Entropy
• Summary

• Get the dataset
• Importing the Libraries
• Importing the Dataset
• Feature Engineering
• Splitting the Dataset into the Training set and Test set

• Traditional Computer Vision
• Image classification using Deep Learning
• Binary and Multi class Image classification
• Deep learning in Object Detection (SSD, YOLO)
• Custom Object recognition Training

• NLP Overview
• Use of NLP
• Library and Frameworks
• Why NLP is difficult?

• Spacy Basics
• Tokenization
• Stemming
• Lemmatization
• Stop Words
• Word segmentation
• Part-of-speech tagging
• Name Entity Recognition
• Deep Learning for NLP

• Encoder
• Decoder
• LSTM
• Attention
• Sequence to Sequence Models
• Sequence to Sequence Models Architecture
• Current research on NLP

• Speech Recognition
• Natural Language Understanding
• Natural Language Generation
• Attention Mechanism
• BERT
• Transformers
• GPT

• Learning Objectives
• Intro to Autoencoders
• Autoencoder Structure
• Autoencoders

• Foundations of Reinforcement Learning
• Policy-Based Methods
• Value-Based Methods
• Policy-Based Methods
• Deep Q-Learning
• Applications

• Project 1: Face Detection
• Project 2: Binary and Multi Image Classification
• Project 3: Object Recognition
• Project 4: Name Entity Recognition for Resumes
• Project 5: Text Classification
• Project 6: Sentiment Analysis