Full Stack Generative Ai: Deep Learning, Cnn, Llm Agentic Ai

Full Stack Generative Ai: Deep Learning, Cnn, Llm Agentic Ai
Published 8/2025
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz

Python, NumPy, Pandas, Matplotlib, Deep Learning, Generative AI : GAN, VAE, LLMs, RAG, MCP, ACP, A2A, Agentic AI & more

What you’ll learn

Design and implement Generative AI models such as GANs, VAEs, Diffusion Models, and Large Language Models, including Retrieval-Augmented Generation (RAG).

Build autonomous AI agents using Agentic AI frameworks like LangChain and apply protocols such as MCP, ACP, and A2A

Understand and train deep learning models, building a strong foundation for advanced AI concepts.

Write Python programs and perform data manipulation and visualization using NumPy, Pandas, and Matplotlib.

Requirements

Description

Overview

Section 1: Course Introduction and Table of Contents

Lecture 1 Course Introduction and Table of Contents

Section 2: Introduction to Generative AI, Machine Learning and Deep Learning

Lecture 2 Generative AI vs Discriminative AI

Lecture 3 Introduction to Popular Generative AI Models

Lecture 4 Introduction to AI and Machine Learning

Lecture 5 Introduction to Deep learning and Neural Networks

Section 3: Setting up Computer

Lecture 6 Setting up Computer – Installing Anaconda

Section 4: Python Programming Basics

Lecture 7 Python Basics – Assignment

Lecture 10 Python Basics – List and Tuples

Section 5: Basic Python ML Library Basics: Numpy, Pandas & Matplotlib

Section 6: Deep Learning and Convolutional Neural Networks

Lecture 19 Installing Deep Learning Libraries

Lecture 21 Activation Functions Introduction

Lecture 22 Popular Types of Activation Functions

Lecture 23 Popular Types of Loss Functions

Lecture 24 Popular Optimizers

Lecture 25 Popular Neural Network Types

Lecture 26 King County House Sales Regression Model – Step 1 Fetch and Load Dataset

Lecture 31 Step 5 and 6 Compile and Fit Model

Lecture 32 Step 7 Visualize Training and Metrics

Lecture 33 Step 8 Prediction Using the Model

Lecture 35 Step 1 – Fetch and Load Data

Lecture 38 Step 4 – Defining the model

Lecture 39 Step 5 – Compile Fit and Plot the Model

Lecture 43 Redwine Quality MultiClass Classification Model – Introduction

Lecture 44 Step1 – Fetch and Load Data

Lecture 45 Step 2 – EDA and Data Visualization

Lecture 46 Step 3 – Defining the Model

Lecture 47 Step 4 – Compile Fit and Plot the Model

Lecture 48 Step 5 – Predicting Wine Quality using Model

Lecture 49 Serialize and Save Trained Model for Later Usage

Lecture 50 Digital Image Basics

Lecture 56 Keras Directory Image Augmentation

Lecture 57 Keras Data Frame Augmentation

Lecture 58 CNN Basics

Lecture 59 Stride Padding and Flattening Concepts of CNN

Lecture 60 Flowers CNN Image Classification Model – Fetch Load and Prepare Data

Lecture 61 Flowers Classification CNN – Create Test and Train Folders

Lecture 65 Flowers Classification CNN – Training and Visualization

Lecture 66 Flowers Classification CNN – Save Model for Later Use

Lecture 67 Flowers Classification CNN – Load Saved Model and Predict

Lecture 68 Flowers Classification CNN – Optimization Techniques – Introduction

Lecture 69 Flowers Classification CNN – Dropout Regularization

Lecture 70 Flowers Classification CNN – Padding and Filter Optimization

Lecture 71 Flowers Classification CNN – Augmentation Optimization

Lecture 74 Transfer Learning using Pretrained Models – VGG Introduction

Lecture 77 ResNet50 Prediction

Lecture 80 VGG16 Transfer Learning Flower Prediction

Lecture 81 VGG16 Transfer Learning using Google Colab GPU – Preparing and Uploading Dataset

Lecture 82 VGG16 Transfer Learning using Google Colab GPU – Training and Prediction

Lecture 83 VGG19 Transfer Learning using Google Colab GPU – Training and Prediction

Lecture 84 ResNet50 Transfer Learning using Google Colab GPU – Training and Prediction

Section 7: Popular CNN and Generative Network Types

Lecture 85 Popular CNN and Generative AI Network Types

Section 8: Type 1: GAN – Generative Adversarial Networks

Lecture 86 Generative Adversarial Networks GAN Introduction

Lecture 90 Generator and Discriminator Mechanism Explained

Lecture 91 A fully Connected Simple GAN using MNIST DataSet – Introduction

Lecture 92 Fully Connected GAN – Loading the Dataset

Lecture 97 Fully Connected GAN – Combining Generator and Discriminator Models

Lecture 98 Fully Connected GAN – Compiling Discriminator and Combined GAN Models

Lecture 102 Fully Connected GAN – Generator Training

Lecture 103 Fully Connected GAN – Saving Log at Each Interval

Lecture 104 Fully Connected GAN – Plot the log at intervals

Lecture 107 Saving the Trained Generator for Later Use

Lecture 108 Generating fake images using the saved GAN Model

Lecture 109 Fully Connected GAN vs Deep Convoluted GAN

Lecture 110 Deep Convolutional GAN – Loading the MNIST Hand Written Digits Dataset

Lecture 113 Deep Convolutional GAN – Defining the Discriminator Function

Lecture 114 Deep Convolutional GAN – Combining and Compiling the Model

Lecture 115 Deep Convolutional GAN – Training the Model

Lecture 116 Deep Convolutional GAN – Training the Model using Google Colab GPU

Lecture 117 Deep Convolutional GAN – Loading the Fashion MNIST Dataset

Lecture 118 Deep Convolutional GAN – Training the MNIST Fashion Model using Google Colab GPU

Lecture 119 Deep Convolutional GAN – Loading CIFAR-10 Dataset and Defining the Generator – 1

Lecture 120 Deep Convolutional GAN – Loading CIFAR-10 Dataset and Defining the Generator – 2

Lecture 121 Deep Convolutional GAN – Defining the Discriminator

Lecture 122 Deep Convolutional GAN CIFAR 10 – Training the Model

Lecture 123 Deep Convolutional GAN – Training the CIFAR10 Model using Google Colab GPU

Lecture 124 Vanilla GAN vs Conditional GAN

Lecture 125 Conditional GAN – Defining the Basic Generator Function

Lecture 128 Conditional GAN – Defining the Basic Discriminator Function

Lecture 129 Conditional GAN – Label Embedding for Discriminator

Lecture 130 Conditional GAN – Combining and Compiling the Model

Lecture 133 Conditional GAN – Display Generated Images

Lecture 134 Conditional GAN – Training the MNIST Model using Google Colab GPU

Lecture 135 Conditional GAN – Training the Fashion MNIST Model using Google Colab GPU

Lecture 138 VAE for MNIST Digits – Importing Libraries

Lecture 139 Initializing VAE Class and Define Encoder

Lecture 140 Defining the Encoder Decoder functions

Lecture 141 The Reparametrization Trick

Lecture 142 Define the Reparametrization Function

Lecture 143 Define the Forward Pass Function

Lecture 144 Define the Loss Function

Lecture 145 Define Transform and Load Dataset

Lecture 146 Running the Training Epochs

Lecture 147 Generating Digit Images using the Trained Model

Lecture 148 Generating only Specific Digit using Conditional VAE

Section 10: Type 3: Autoregressive Models – Natural Language Processing Fundamentals

Lecture 149 Introduction to Autoregressive Models

Lecture 152 NLP Text Prediction

Section 11: Type 3: Autoregressive Models – Transformers and LLMs

Lecture 153 Introduction to Transformers

Lecture 154 Popular Transformer Models

Lecture 155 Implementing a PreTrained GPT2 Model

Lecture 156 Comparing GPT with Deepseek

Lecture 157 Implementing a Pretrained DeepseekR1 Model

Section 12: LLM Customization – Fine Tuning and RAG (Retrieval-Augmented Generation)

Lecture 158 LLM Customization – Fine Tuning vs RAG

Lecture 162 RAG Introduction

Section 13: Agentic AI Fundamentals

Lecture 166 Introduction to Agentic AI

Section 14: Popular Agentic AI Protocols – MCP, ACP, A2A

Lecture 172 Popular Agentic AI Protocols

Lecture 173 Implementing MCP in our Agentic AI File Processor

Lecture 174 Introduction to ACP – Agent Communication Protocol

Lecture 178 Introduction to A2A – Agent to Agent Protocol

Lecture 179 A2A File Processing

Section 15: AI Agent Frameworks

Lecture 180 Introduction to AI Agent Frameworks

Section 16: Generative AI: Diffusion Models

Lecture 185 Introduction to Diffusion Models and Stable Diffusion

Lecture 186 Image Generation using Pretrained Stable Diffusion Model

Section 17: SOURCE CODE DOWNLOAD

Lecture 187 Download Source Code and Datasets