Python with Artificial Intelligence (AI) Training

• Values and types
• Variables
• Variable names and keywords
• Operators and operands
• Expressions and statements
• Interactive mode and script mode
• Order of operations
• String operations
• Comments
• Debugging

• Function calls
• Type conversion functions
• Math functions
• Composition
• Adding new functions
• Definitions and uses
• Flow of execution
• Parameters and arguments
• Variables and parameters are local
• Stack diagrams
• Fruitful functions and void functions
• Why functions?
• Importing with from
• Debugging

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

• Return values
• Incremental development
• Composition
• Boolean functions
• More recursion
• Leap of faith
• Checking types
• Debugging

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

• A string is a sequence
• Len
• Traversal with a for loop
• String slices
• Strings are immutable
• Searching
• Looping and counting
• String methods
• The in operator
• String comparison
• Debugging

• A list is a sequence
• Lists are mutable
• Traversing a list
• List operations
• List slices
• List methods
• Map, filter and reduce
• Deleting elements
• Lists and strings
• Objects and values
• Aliasing
• List arguments
• Debugging

• Dictionary as a set of counters
• Looping and dictionaries
• Reverse lookup
• Dictionaries and lists
• Memos
• Global variables
• Long integers
• Debugging

• Tuples are immutable
• Tuple assignment
• Tuples as return values
• Variable-length argument tuples
• Lists and tuples
• Dictionaries and tuples
• Comparing tuples
• Sequences of sequences
• Debugging

• Usage
• Union, Difference
• Available methods

• Introduction
• Exceptions versus Syntax Errors
• Raising an Exception
• The AssertionError Exception
• The try and except Block: Handling Exceptions
• The else Clause       

• Persistence
• Reading and writing
• Format operator
• Filenames and paths
• Catching exceptions
• Databases
• Writing modules
• Debugging

• Introduction, Application and Usage
• reader and writer
• DictReader and DictWriter
• Simple CSV processing using functional programming

• Introduction to Pandas
• DataFrame Data Structure
• DataFrame Indexing and Loading
• Querying a DataFrame
• Indexing Dataframes
• Manipulating DataFrame

• Installations
• Introduction, Application and Usage
• Basic Structured Query Language
• CRUID operations

• Principles of Information Visualization
• Visualizing Data Using Spreadsheets
• Matplotlib
• Plotly
• Scatterplots
• Line Plots
• Bar Charts
• Histograms
• Plotting with Pandas

• User-defined types
• Attributes
• Real World Example
• Instances as return values
• Objects are mutable
• Copying
• Debugging

• Object-oriented features
• The self
• Printing objects
• The init method
• The __str__ method
• Other special methods
• Operator overloading
• Type-based dispatch
• Polymorphism
• @staticmethod
• Debugging

• Introduction
• Checking callable or not
• Decorators
• Creating and using decorators

• Introduction
• Example
• Class attributes
• Private, Protected and Public
• Multiple Inheritance
• Class diagrams
• Debugging
• Data encapsulation

• Installing Git
• status, log, commit push, pull commands 
• Branch, Tags and Multiple remote concept and Implementation
• checkout, reset, rebase, merge concept
• Gitlab vs Github vs Bitbucket

As per the recommendation of students, one of the following projects will be done by the instructor themselves!

• Web Scraping project (includes handling web scraping tools, proper file handling and implementation of sql)
• GUI project (any desktop application e.g: calculator, 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
• 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