AI Engineering (Batch-02)

Wishlist Share
Share Course
Page Link
Share On Social Media

Course Content

Introductory Class

  • AI Engineering (Batch-02) – Introductory Session
    02:13:00

Class 01 – Anaconda Setup | Intro to Python | Data Types (Numbers, Float, String) | Formatted Strings | Built-in Functions

Class 02 – Data Types (Lists, Tuples, Sets, Booleans, Dictionaries) | Built-in Functions

Class 03 – Python Fundamentals | if-elif-else | Comparison & Logical Operators | for & while Loops

Class 04 – Lambda & User-Defined Functions | Intro to Python Libraries | NumPy (1D/2D/3D Arrays, Indexing, Functions) | Matplotlib Basics & Plotting Graphs

Class 05 – Introduction to Pandas | Exploratory Data Analysis (EDA) | Data Pre-processing | Importing Excel/CSV Files | Visualizations with Matplotlib & Seaborn | Correlation & Heatmaps

Class 06 – Real-World Python Projects – PDF Merger, Watermarking, Text/Image Extraction | Email Sender with Static/Dynamic Content | Audio-to-Text Transcription & Urdu Translation | Use Cases & Opportunities Overview

Class 07 – Introduction to Machine Learning & Its Types (Supervised, Unsupervised, Reinforcement) | Features Explained | Converting Categorical to Numerical Data

Class 08 – Evaluation Metrics (Confusion Matrix, Accuracy, Precision, Recall, F1 Score) | Feature Scaling | Logistic Regression & SVM – Theory & Implementation | Making Predictions on New Data

Class 09 – Machine Learning: Standardization & Normalization | Decision Tree – Scikit-Learn & Manual Implementation

Class 10 – Machine Learning: Random Forest Implementation | Underfitting vs. Overfitting | Bias-Variance Tradeoff | ROC & AUC Curves | Introduction to KNN

Class 11 – Machine Learning: KNN Implementation | Linear Regression (Simple & Multiple) | Regression Metrics: MAE, MSE, RMSE, R²

Class 12 – Machine Learning: DBSCAN and HDBSCAN – Explanation and Implementation

Class 13 – Machine Learning: Association Rule Learning – Apriori & FP-Growth Implementation | Streamlit Setup & Configuration in VS Code

Class 14 – Machine Learning: Naive Bayes Algorithm – Explanation and Implementation | Streamlit Setup & Configuration

Class 15 – Machine Learning: Class Imbalance Handling | Resampling Techniques (SMOTE, Tomek Links, ENN) | Model-Level & Metric-Level Solutions | Implementation & Best Practices

Class 16 – Machine Learning: Ensemble Learning Methods | Bagging, Boosting, Stacking & Voting Classifier | XGBoost & AdaBoost Implementation | Advanced Ensemble Techniques

Class 17 – Flask Framework: Web Development Fundamentals | Routes, GET/POST Methods & Project Structure | Virtual Environment Setup | Project 01: To-Do List App | Project 02: Weather Forecasting App with OpenWeatherMap API

Class 18 – Flask Framework: Advanced Implementation | ML Model Deployment using Pickle Library | Student Issue Resolution | Project: IRIS Flower Prediction AI App | Model Serialization & Web Integration

Class 19 – Deep Learning: Introduction to Neural Networks | Neurons, Input/Hidden/Output Layers | Single & Multi-Layer Perceptron Theory & Implementation | Activation Functions & Backpropagation

Class 20 – Deep Learning: Convolutional Neural Networks (CNN) | CNN Architecture Components | Explanation of Kernels/Filters, Stride, Padding & Pooling Layers | Project: Face Mask Detection & Hand Gesture Recognition using MediaPipe & CNN

Class 21 – Deep Learning & SQL: Face Mask Detection | Detailed Code Walkthrough | Introduction to SQL | SELECT & WHERE Clauses | Table Fundamentals

Class 22 – SQL: WHERE Clause Filters | IN, LIKE & Comparison Operators | SQL Joins (INNER, LEFT, RIGHT, OUTER) | Aggregate Functions | Nested Queries

Class 23 – Deep Learning & SQL: Connecting SQL with Python | Recurrent Neural Networks (RNN) – Architecture & Working | Basic RNN Implementation | Project: Next Word Prediction using Custom Text Data

Class 24 – Deep Learning: Recurrent Neural Networks (RNN) | Types of RNNs | Long Short-Term Memory (LSTM) & Bi-Directional LSTM – Detailed Explanation

Class 25 – Deep Learning: Project: Next Word & Character Prediction using Custom RNN Model | Top-5 Match Predictions with Relevance Scores | Python Case Study: Exploratory Data Analysis (EDA) on a Retail Clothing Brand

Class 26 – Deep Learning: Transformer Neural Networks | Word Embedding Techniques (Word2Vec) | Transformer Architecture & Self-Attention Mechanism | Project: News Summarization using Facebook/BART-Large-CNN (Summarizing 2000–4000 Word Articles into 500–600 Words)

Class 27 – Generative AI: Introduction to Large Language Models (LLMs) | Accessing Pre-Trained LLMs via APIs (OpenAI ChatGPT, DeepSeek, GROQ) | Understanding Pricing Models & Tokenization | Projects: Simple Chatbot using GROQ API (Llama 3.3 70B) | Chatbot using DeepSeek API

Class 28 – Hugging Face Overview | Inference & Spaces | Text-to-Text & Text-to-Image Models | Vector Databases | RAG Architecture & Workflow | Project: PDF-Based RAG Chatbot using GROQ

Class 29 – Generative AI (LangChain Part 1): LangChain Framework Overview | Core Components (Loaders, Splitters, Embeddings, Vector Stores) | Project: PDF-Based Chatbot using LangCh

Class 30 – Generative AI: Prompt Engineering Masterclass | Zero-Shot, One-Shot & Few-Shot Prompting | Chain-of-Thought, Self-Consistency & ReAct Prompting | Real-World Working Examples | Importance of Prompting in Modern AI Systems

Class 31 – Generative AI: LangChain Framework – Detailed Breakdown of Core Components: Models, Prompt Templates, LLM Chains (Simple & Sequential), Memory Module | Conversation Buffer Memory | Practical Hands-On Examples | Understanding NSFW Content Handling

Class 32 – Agentic AI: Introduction to Agentic AI | Concepts, Workflow & Real-World Use Cases | Step-by-Step Implementation

Short Discussion

Class 34 – Agentic AI: Practical Project Development

Class 35 –

Class 36 – Agentic AI: CrewAI Framework – Core Components Explained | How CrewAI Operates | Multi-Agent Collaboration Workflows | Hands-On Implementation

Class 37 – Agentic AI: n8n Automation Platform – Introduction & Workflow | What is n8n? | Building AI-Powered Automations