Course Outline

• Python Foundation

  • Introduction to Python programming
  • Variables and data types
  • Control Flow
  • Data Structures in Python
  • String Manipulation
  • Classes and Objects, File handling
  • Packages, PIP
  • Pandas, Data Frames
  • Coding Project: Employee Management System.

• Data Science Foundation

  • What is Data Science?
  • Difference between AI. ML, Deep Learning
  • Mean, Median, Mode, Std Deviation
  • Distributions, CLT, Pareto, Confidence Intervals
  • Hypothesis Testing, Gradient Descent
  • Dimensionality Reduction, Overfitting, Underfitting
  • Univariate, Multivariate Analysis
  • Bayes Theorem, Z-Score, P-value, Skewness
  • T-Test, Chi-Squared Tests, Anova
  • Descriptive, Prescriptive and Predictive Analytics
  • Coding exercise: Data pre-processing of House Price Prediction

• Machine Learning

  • Introduction to Machine Learning
  • Supervised & Unsupervised Learning
  • Feature Engineering
  • Regression - Linear, Logistic, etc
  • Classification - Single and Multi-class
  • SVM, KNN, Naive Bayes,
  • Decision Tree, Random Forest, Ensemble
  • Optimization
  • K-Fold, Adaboost, XGBoost
  • Clustering - KMeans, DBScan, etc
  • Coding exercise 1: Text Classification with SVM, Random Forest, and KNN
  • Coding exercise 2: Email spam detection using logistic regression

• Deep Learning

  • Introduction to Deep Learning
  • Artificial Neural Network
  • Perceptrons, Feed Forward, Backpropagation
  • Convolutional Neural Networks - CNN
  • Recurrent Neural Networks - RNN
  • Long Short Term Memory (LSTM), GRU
  • Association Rule Learning
  • Reinforcement Learning
  • Q-Learning, Policy-Based Learning
  • Coding exercise 1: Speech recognition project
  • Coding exercise 2: Stock Market prediction using RNN.

• Development Tools - VS Code, Git, Jupyter, etc.

  • Programming environment for Data Science
  • Anaconda, Jupyter, Pycharm
  • Working with Jupyter notebook and Google Colab
  • Installing VS Code for AI/ML programming
  • Configuring and running applications in VS Code
  • Source Code Control - what is Git?
  • Git commands - Checkout, Push, Pull, Commit
  • Tagging, Branching, and Merging
  • Creating your first ML program repo in Git
  • Working in distributed teams in multinational companies
  • Coding Exercise: House Price Prediction ML Project using all the tools

• Computer Vision

  • What is Computer Vision?
  • Image Classification
  • Use cases for Manufacturing, Healthcare, Hospitality
  • Face & Emotion Detection, Object Detection
  • Haar Cascade, MT-CNN, R-CNN
  • YOLO V4, 5, 6, 7, and more
  • D-Lib for face landmark detection
  • Racism & Terrorism Detection using Vgg-16 and more
  • Coding Exercise 1: Nervousness detection of candidates taking exam
  • Coding Exercise 2: Object detection for dangerous objects in Airports

• SQL For Data Science

  • Relational Databases
  • NoSQL, GraphQL, Vector DB
  • Selects and Joins
  • Where clause, Group By, and more
  • Clustered and Non-clustered Indexes
  • Writing complex queries with Joins, conditions, subqueries
  • Coding Exercise: Generating Sales data forecast report

• Model deployment - flask API

  • What is MLOps
  • Why is it important to learn deployment
  • How to deploy models on production?
  • Data Store and Model store
  • Weights, File formats, Pytorch, and more
  • Coding exercise: Build an ML model and deploy on AWS

• Tensorflow and Pytorch

  • What is Tensorflow?
  • The Tensorflow Playground
  • Writing a CNN application using Tensorflow
  • Keras and Pytorch
  • How to create Pytorch models and deploy them
  • Coding Exercise: ML application using Tensorflow

• Generative AI

  • Understanding the requirements
  • Steps to create your own chatbot
  • Designing the solution
  • Creating the chatbot using OpenAI and other LLMs
  • Creating additional features for your chatbot
  • Training your chatbot with your custom content
  • Feeding Excel sheets, transactional data from databases
  • Taking data from MySQL, SQL Server, Postgres

• Conclusion and Next Steps

  • Quick recap
  • Summarizing what we learned
  • Where to go from here?
  • How to become an expert developer with an Internship
  • Next steps and action items