GenAI Pinnacle Program

A Comprehensive and Industry-Aligned Curriculum

Table of Contents

Demystifying the World of Generative AI

Introduction to GenA

Human Decision Making and its Biase

Structured Approach to Problem Solving

Large Language Models

Getting Started with LLM

Building LLM Apps using Prompt Engineerin

Building End-to-End Generative AI Application

Building Production ready RAG systems using LlamaInde

Finetuning LLM

Training LLMs from Scratc

Responsible AI in the Generative AI Era

Stable Diffusion Models

Getting Started with Stable Diffusio

Mastering Methods and Tools of Stable Diffusio

Advanced Stable Diffusion Techniques

 Basic of Machine Learning and Python

Python for Data Scienc

Data Exploration and Statistical Inferenc

Basics of Machine Learnin

Fundamentals of Deep Learnin

Introduction to Natural Language Processing (NLP

Exploring Natural Language Processing (NLP) using

Deep Learning
Curriculum Overview

The GenAI Pinnacle program is meticulously crafted

in response to the burgeoning demand for Generative

AI technology, featuring elite instructors renowned

for their profound expertise in the field.

Our comprehensive curriculum delves into Large

Language Models, Stable Diffusion Models, and the

foundational elements of Data Science and Machine

Learning, preparing you to excel in the rapidly evolving

landscape of Generative AI.

200+ Hours of Learning

26+ Tools, Libraries & Frameworks

10+ Generative AI Projects

15+ Assignments to Practice

Demystifying the World of
Generative AI
Introduction to Generative AI
What is Generative AI
How does Gen AI work
Text Generation with Gen A
Image Generation with Gen A
Course overvie
Meet your instructors

Human Decision-Making and Its Biases

Why Decision Making is Hard

Human Decision Making - An Introduction

Introduction to the Course

Making Better Decisions - An Introduction

Mathematical Thinking

The Brain on Decisions

Everyday Decisions

The VUCA World

 Decisive (Chip & Dan Heath)

Case Study - The Monty Hall Problem

Case Study - The Monty Hall Problem Analysis

Data in Decision Making

Case 1: The Art of Data (and War) - Armoring

Planes for Additional Safety

How Algorithms Can Help

But Algorithms Aren’t the Panacea

Thinking Fast & Slow (Daniel Kahneman)

Simpson's Paradox and Significance of Business Intuition

Bringing Data to Intuition and Vice Versa

Group Decision Making: Understanding Perceptions

and Biases

12 Angry Men - Exploring Human Nature

12 Angry Men - The Movie

12 Angry Men - Unpacking the Case

12 Angry Men - The Challenge of Dissenting Voices

12 Angry Men - Confirmation Bias and the Complexities

12 Angry Men - Ten Decision-Making Lessons (Part A)

12 Angry Men - Ten Decision-Making Lessons (Part B)

Group Decision Making - Role of Context, Hierarchy

and Emotional Dynamics
Challenger Launch Case - A Tragic Beginning

Challenger Launch Case - Analyzing the Data

Challenger Launch Case - Resulting vs. Decision Quality

Challenger Launch Case - Uncovering Critical Data

Challenger Launch Case - Normalization of Deviant

Behavior

Context and Decision Environments: Challenger

Launch Case vs. 12 Angry Men

Advocacy vs. Inquiry: Shaping Decision-Making

Type One and Type Two Decisions

Organizational Decision Making - Assumptions and Myths

Building a Decision Making Framework

Conclusion

Reading: Case Study - The Space Shuttle Challenger

Disaster

Structured Approach to Problem Solving

Structured Thinking

Structred Approach to Problem Solving

Introduction to Structured Thinking

 Course Introduction

The Global Problem Statement

Introduction to Structured Thinking?

Some frameworks used in Structured Thinking

Structured Thinking and Problem Solving

Can Structured Thinking help in solving Business Problem

Solving Problems Like a Pro

Check Your Understanding

Defining problem statements - Part 1

Framing the Problem Statement

The Common Pitfalls — The Loop Trap

The Common Pitfalls — The Complexity Trap

The Common Pitfalls — The Obvious Trap

Check Your Understanding

End of Module Graded Quizt

Defining problem statements - Part 2

Defining a Problem Statement Worksheet (PSW)

How the PSW Helps in Defining a Problem Statement

Best Practices and Pitfalls of a PSW

Check Your Understanding

 Creating a PSW

Frameworks of Problem Solving

Mutually Exclusive and Collectively Exhaustive (MECE)

What is an Issue Tree?

Creating an Issue Tree

What is a Hypothesis Tree?

Other Frameworks for Problem-Solving

Check Your Understanding

Finalizing the Solution

Documenting the Implementation Phase

The Adoption Plan

Metrics for Evaluation-1

Metrics for Evaluation-2

Creating User Research for Insights

Check Your Understanding

Checks to do before Solution

Common Design Pitfalls

Common Strategic Pitfalls

Phases of Testing a DS Project

Check Your Understanding

 End of Module Graded Quiz

Human-Centered Design
Human-Centered Design (HCD) and Empathy

Optional Reading - User Centered Design in

a Product Development Lifecycle Process

What is HCD?

Empathy Map — Why and How

The Discovery Phase

Empathy Map, User Persona, and User Flow

The Solution Phase

Fireside Chat with Biju Dominic

Empathy in Design — Three Strategies to Build

Empathy

Large Language Models

Getting Starting with LLMs

Introduction

The Exponential Growth

The Evolution of NLP

The Evolution of NLP: Symbolic NLP

The Evolution of NLP: Statistical NLP

The Evolution of NLP: Deep Learning Era

The Evolution of NLP: Deep Learning Era II

The Evolution of NLP: Tranformers

What are Large Language Models?

Introduction to Large Language Model

What is a Large Language Model?

Understanding Foundational Models

Different types of LLMs: Based on Response

Different types of LLMs: Based on Model Architecture

The Current State of the Art in LLMs

The Current State of the Art in LLMs

Building LLM Apps using Prompt
Engineering

Introduction
Course Objective

How to build diffferent LLM AppIications?

Introduction to Building Different LLM applications

Prompt Engineering

Retrieval Augmented Generation

Finetuning LLMs

Training LLMs from Scratch

Getting Started with Prompt Engineering

Introduction to Prompt Engineering

Set up your machine for Prompt Engineering

Prompt Engineering with ChatGPT API

Enabling Conversation with ChatGPT API

Best Practices and Guidelines for Prompt Engineering

Introduction to Best Practices and Guidelines for
Prompt Engineering
 Write Clear and Specific Instructions

Use Specific Examples

Vary the Prompts and Iterate

Use the Delimiters

Specify Structured Output Format

Use Temperature Parameter

Prompt Engineering with Open Source LLMs

Introduction to Prompt Engineering with Open

Source LLMs

Set up your machine

Prompt Engineering using Open Source LLMs

Enabling Conversation with Open Source LLMs

Understanding Different Prompt Engineering Techniques

Introduction to Understanding Different Prompt

Engineering Techniques

Few Shot Prompting

One Shot Prompting

Zero Shot Prompting

Building Chatbot on Your Enterprise Data

Building DHSGPT using Prompt Engineering- Part I

Building DHSGPT using Prompt Engineering- Part II

 Building End-to-End Generative AI

Applications
Introduction to Generative AI applications

Overview of generative AI applications and their impact

Understanding Generative AI Applications - Architecture

and Impact

Overview of Tools and Technologies

Applications Across Various Industries

Ethical Consideration

No-code Generative AI app development

Introduction to No-code AI Development

Building GPT Apps with ChatGPT

Hands On-Building with GPT Apps

Building AI Assistants with HuggingChat

Hands On-Building with HuggingChat

Gen AI powered Assistant with Amazon Q

Case study: Popular apps using no-code platforms

Overview of Other Alternatives

 f
Code- ocused Generative AI App Development

Introduction to LangChain, ChatGPT and Gemini Pro

Hands On- LangChain, ChatGPT and Gemini

Interactive Text Chatbot with ChatGPT, Gemini and

LangChain

Hands On: Interactive Text Chatbot with ChatGPT,

Gemini and LangChain

Introduction to Streamlit and Chainlit

Conversational UI Chatbot App with ChatGPT,

LangChain and Chainlit

Hands On- Conversational UI Chatbot App with

ChatGPT, LangChain and Chainlit

Conversational UI Chatbot App with ChatGPT,

LangChain and Streamlit

Hands On- Conversational UI Chatbot App with

with ChatGPT, LangChain and Streamlit

Case study: Developing a Complex Generative AI

application - QA RAG Chatbot

Project- File QA RAG Chatbot App with ChatGPT,

LangChain and Streamlit

Project- File QA RAG Chatbot App with ChatGPT,

LangChain and Chainlit

Course Summary and Way Forward!

Building Production Ready RAG systems

using LlamaIndex

Introduction to RAG systems

Why RAG?

What is RAG system?

Overview of RAG Framework

Quiz

Getting Started with LlamaIndex

Introduction to LlamaIndex

Quiz

Components of LlamaIndex

Code: Build Your First RAG system using LlamaIndex

Components of LlamaIndex

Data Loaders

Embeddings

LLMs

Indexing

Vector Databases

Retriever

 Response Synthesis

Query Engine

Code: Customising the standard RAG Pipeline : Part I

Quiz

Evaluation of RAG systems

Introduction to Evaluation Metrics

Hit Rate and MRR

Faithfulness

Relevancy

Correctness

Evaluating RAG Systems - Part I

Evaluating RAG Systems - Part II

Code: Evaluating different Indices

Quiz

Customization in LlamaIndex

Metadata Management

Metadata Extraction

Data Ingestion pipeline

Code: Customising the standard RAG Pipeline : Part II

Quiz
Advanced approaches for powerful RAG system
Auto Retriever

Sentence Window Retriever

Auto Merging Retriever

Recursive Retriever

Finetuning Embeddings

Router Query Engine and Sub Question Query Engine

Hybrid Fusion Retriever

Multi-Document Agents

Code:Building a powerful RAG system using LlamaIndex

Quiz

 Finetuning LLMs
Introduction to Finetuning LLMs

Introduction and Course Summary

Why and What is Finetuning LLMs?

Research Papers and blogs for additional details

Quiz

Instruction Finetuning in Practice

Module Overview

Finetuning Process

Data gathering and preprocessing

Training

Evaluation

Quiz

Setting up the runpod instance

Full Finetuning LLM to follow instructions

Limitations of Full Finetuning

Research Papers and blogs for additional details

Parameter-Efficient Finetuning (PEFT)

Why Parameter Efficient Finetuning?
 What is Parameter Efficient Finetuning?

Different types of PEFT methods

Quiz

Prompt Learning PEFT Techniques

Overview of Prompt Learning PEFT Techniques

Prompt Tuning

Text Classification on Twitter Complain Dataset

using Prompt Tuning

Prefix Tuning

Adaptation Prompt tuning

Adaptation Prompt Tuning for Product Ad Generation

Quiz

Popular PEFT methods in practice

LoRA and its variants

Hinglish Instruct Finetuning using LoRA

Quantization and QLoRA

Function Calling using QLoRA

IA3 and Bottleneck adapters

Natural Language to SQL query generation using IA3

Training LLMs from Scratch
Introduction to the Course
Course Overview

Training LLMs from Scratch

Introduction to Training LLMs From Scratch

What do you mean by Training LLMs from Scratch?

Why train your own LLMs?

Important Concepts for Training LLMs from Scratch

Chinchilla Scaling Laws

Parallel and Distributed paradigm

Data Parallelism

Model Parallelism

Pipeline Parallelism

Fully Sharded Data Parellelism/ZeRO 3

Tensor Parallelism

2D and 3D Parallelism

Steps involved in Training LLMs from Scratch

Overview of Steps Involved in Training LLMs from

Scratch
 Training Data Curation

Data preprocessing

Tokenization

Model Architecture

Model Evaluation- done

Training your own LLMs from Scratch

Estimate Cost of Training LLMs from Scratch

Hands on - Setting up runpod and intro

Hands on - Dataset curation and preprocessing

Hands on - Training BPE Tokenizer

Hands on - Training LLMs from Scratch using DeepSpeed

ZeRO 3/FSDP Distributed Training on 8 GPUs

Aligining LLM with Human Preferences

Recap of Instruction Following LLM

Introduction to Alignment Methods

Reinforcement Learning from Human Feedback (RLHF)

Aligning LLMs to Human Preferences with RLHF- done

DPO and IPO

Preference tuning LLMs with DPO

What Next?

Recent Advancements

 Responsible AI in the Generative AI Era

Introduction to Responsible AI in the Generative AI Era
Introduction to Responsible AI

Generative AI _ the challenges they bring

Principles of Responsible AI in the Generative AI Era

Reading:The necessary intersection of Generative AI,

Responsible AI & Emotions

Stable Diffusion Models

Getting started with Stable Diffusion
Introduction to Stable Diffusion
Getting Started with stable diffusion

History Behind Stable Diffusion

Stable Diffusion: Shining Star

Stable diffusion 2.0 and 2.1

Paper Review: Fergus and Zeiler Paper

Overview of Stable Diffusion process

Basic Stable Diffusion Intuition

Examples of Basic Stable Diffusion Intuition

Stable Diffusion: Reverse Diffusion

Stable Diffusion: Purpose

Understanding Core Components of Stable Diffusion

UNet

Latents

CLIP - Part I

CLIP - Part II

Summarizing Stable Diffusion

How it all fits in? (Part 1)

How it all fits in? (Part 2)

Runtime Environments

What Next?

Understanding Variational Autoencoders

Introduction to VAE

Working of VAE

Applications of VAE

In depth understanding of stable diffusion - Part I

Forward Process

Noise Schedule

How to code forward process?

Reverse Process

In depth understanding of stable diffusion - Part II

Positional Encoding

Loss Function

Components of Diffusion Model

Implement DDPM from scratch

Understanding the problem statement

Hands-on with DDPM from scratch- 1

Hands-on with DDPM from scratch- 2

Hands-on with DDPM from scratch- 3

Hands-on with DDPM from scratch- 4

Hands-on with DDPM from scratch- 5

Hands-on with DDPM from scratch- 6

Hands-on with DDPM from scratch- 7

 Mastering Methods & tools of stable

diffusion
Understanding Dalle 2
The Future Roadmap

Understanding Text Conditioning with Dalle 2

Open AI CLIP

Overview of training process

Glide

Training Pathways for Dalle 2

Steps involved in training stable diffusion

Training from Scratch vs Finetuning

How to Train Stable Diffusion at Scale?

Ethical Implications

Stable Diffusion Deep Dive Hands-on- Setup and

Whole Generation

Stable Diffusion Deep Dive Hands-on - Auto Encoders

Stable Diffusion Deep Dive Hands-on - The Scheduler

Stable Diffusion Deep Dive Hands-on - Text and

Positional Embedding

Stable Diffusion Deep Dive Hands-on - Experiments with

Embeddings

 Stable Diffusion Deep Dive Hands-on - Textual Inversion

Mastering stability.ai and its tools

Introduction to Stability.AI

How to use Stability.AI tools?

Review of Deployment Options for SD WebUI

Automatic1111 WebUI on RunPod GPU environment

SD WebUI Hands-On - Installation and Setup

SD WebUI Hands-On - Generation and Settings

Prompt Engineering Concepts for Stable Diffusion

Analyzing Prompts and Prompts Matrix

Prompt Strengths and Weights

Prompt Editing and Blending

XYZ Plots and Dream Studio

Advanced Stable Diffusion Techniques

Img2img
Course Overview

img2img: Categorical Intuition

Image In-Painting: Various forms and factors

Image Editing

Hands-on: img2img - Vanilla prompt based transformation

Hands-on: img2img - Image in-painting

Hands-on: img2img - Sketch and in-paint sketch

CIVITAI
Introduction to CIVITAI

Stable Diffusion: Extensions

MidJourney
MidJourney: Storm & Story

MidJourney: Inspiration

MidJourney: How to use?

MidJourney: Alternatives

InstructPix2Pix Paper review and ControlNet

Paper Review: InstructPix2Pix Overview and Setup

ControlNet: Introduction and Setup

ControlNets OpenPose

Upscaling Images with SD & ControlNets

Basics of Machine Learning and

Python

Python for Data Science

Basics of Python

Explore Python for Data Science

Important libraries and functions in Python

Reading files and manipulating data in Python

Working with data frames, lists, and dictionary

Data Exploration and Statistical Inference

Use Matplotlib and Seaborn for data visualization

Creating charts to visualize data and generate Insights

Univariate and Bivariate analysis using Python

Perform Statistical Analysis on real-world datasets

Build and Validate Hypothesis using statistical tests

Generating useful insights from the data

Basics of Machine Learning

Learn Important Machine Learning concepts

Perform data cleaning and Preprocessing

 In-depth understanding of the Basics prediction models
k-NN, Linear Models, Decision Tree
Math Behind Each Machine Learning Algorithm
k-NN, Linear Models, Decision Tree
Math Behind Each Machine Learning Algorithm
Advanced algorithms like Bagging and Boosting, SVM,
Naive Bayes
Hyperparameter Tuning to improve model
Solving real-world business problems using Machine
Learning

Fundamentals of Deep Learning

Essential Concepts of Deep Learning
Working on Neural Network from Scratch
k-NN, Linear Models, DeciActivation Functions and
Optimizers for Deep Learningsion Tree
Understand Deep Learning architectures (MLP, CNN,
RNN, LSTM, GRUs)
Explore Deep Learning Framework, PyTorch
Learn to tune the hyperparameters of Neural Networks
Build Deep Learning models to tackle real-life problems
Use Transfer Learning for training models
 Applied Machine Learning

Building Your ML model: KNN

Introduction to sklearn

Introduction to KNN

Building a KNN model

Determining right value of k

Selecting the right model

Overfitting and Underfitting

Implementing KNN algorithm

Selecting the right model

Introduction to Overfitting and Underfitting

Visualizing Overfitting and Underfitting using kNN

Selecting the right model

Bias Variance tradeoff

Evaluation metrics

Introduction to Evaluation Metrics

Confusion Matrix

Accuracy

Precision and Recall

 Evaluation metrics for Regression

R2 and Adjusted R2

Linear Regression

Introduction to Linear Models

Understanding Cost Function
Understanding Gradient Descent
Maths behind Gradient Descent
Covexity of Cost Function
Assumptions of Linear Regression
Implementing Linear Regression

Logistic Regression

Introduction to Logistic Regression

Odds Ratio

Building your first Predictive model

Introduction and Overview

Quiz: Introduction and Overview
Preparing the Dataset
Quiz:Preparing the Dataset
Build a Benchmark Model: Regression
 Quiz:Build a Benchmark Model: Regression
Benchmark Model: Regression Implementation
Quiz: Benchmark Model - Regression Implementation
Build a Benchmark Model: Classification
Quiz: Build a Benchmark Model - Classification
Benchmark Model: Classification Implementation
Quiz: Benchmark - Classification Implementation

Evaluation Metrics
Introduction to Evaluation Metrics
Quiz: Introduction to Evaluation Metrics
Confusion Matrix
Quiz: Confusion Matrix
Accuracy
Quiz: Accuracy
Alternatives of Accuracy
Quiz: Alternatives of Accuracy
Precision and Recall

Quiz: Precision and Recall

Thresholding
Quiz: Thresholding
AUC-ROC
 Quiz: AUC-ROC
Log loss
Quiz: Log loss
Evaluation Metrics for Regression
Quiz: Evaluation Metrics for Regression
R2 and Adjusted R2

Quiz: R2 and Adjusted R2

Preprocessing Data
Dealing with Missing Values in the Data

Quiz: Dealing with missing values in the data

Replacing Missing Values

Quiz: Replacing Missing values

Imputing Missing Values in data

Quiz: Imputing Missing values in data

Working with Categorical Variables

Quiz: Working with categorical data

Working with Outliers

Quiz: Working with outliers

Preprocessing Data for Model Building
Build Your First ML Model: k-NN
Introduction to k-Nearest Neighbours

Quiz: Introduction to k-Nearest Neighbours

Building a kNN model

Quiz: Building a kNN model

Determining right value of k

Quiz: Determining right value of k

How to calculate the distance

Quiz: How to calculate the distance

Issue with distance based algorithms

Quiz: Issue with distance based algorithms

Introduction to sklearn

Implementing k-Nearest Neighbours algorithm

Quiz: Implementing k-Nearest Neighbours algorithm

Selecting the Right Model
Introduction to Overfitting and Underfitting Models
Quiz: Introduction to Overfitting and Underfitting Models
Visualizing overfitting and underfitting using knn

Quiz: Visualizing overfitting and underfitting using knn

Selecting the Right Model

 What is Validation?

Quiz: What is Validation

Understanding Hold-Out Validation

Quiz: Understanding Hold-Out Validation

Implementing Hold-Out Validation

Quiz: Implementing Hold-Out Validation

Understanding k-fold Cross Validation

Implementing k-fold Cross Validation

Quiz: Understanding k-fold Cross Validation

Bias Variance Tradeoff

Quiz: Bias Variance Tradeoff

Linear Models

Introduction to Linear Models

Quiz: Introduction to linear model
Understanding Cost function

Quiz: Understanding Cost function

Understanding Gradient descent (Intuition)

Maths behind gradient descent

Convexity of cost function

Quiz: Convexity of Cost function

Quiz: Gradient Descent

Assumptions of Linear Regression

Quiz: Assumptions of linear model

Implementing Linear Regression

Generalized Linear Models

Quiz: Generalized Linear Models

Introduction to Logistic Regression

Quiz: Introduction to logistic regression

Quiz: Logistic Regression

Odds Ratio

Implementing Logistic Regression

Multiclass using Logistic Regression

Quiz: Multi-Class Logistic Regression

Challenges with Linear Regression

Quiz: Challenges with Linear regression

Introduction to Regularisation

Quiz: Introduction to Regularization

Implementing Regularisation

Coefficient estimate for ridge and lasso (Optional)

Fundamentals of Deep Learning
Introduction to Neural Networks
Perceptron

Weights in Perceptron

Multi Layer Perceptron

Visualizing the neural network

Understanding Decision Boundary

Forward and Backward Prop Intuition

Gradient Descent algorithm

Activation Functions
Why do we need activation functions?

Linear Activation Function

Sigmoid and Tanh

ReLU and Leaky ReLU

Softmax

Tips to select right activation function

Optimizers
Variants of Gradient Descent

Problems with Gradient Descent

 RMSProp

Adam

Loss Functions

Introduction to Loss Function

Binary and Categorical Cross Entropyt

Getting Started with Image Data

Introduction to PyTorch and Tensors

Mathematical and Matrix Operations: Part I
Mathematical and Matrix Operations: Part II

Mathematical and Matrix Operations: Part III

Solving image classification using MLP - Part I

Solving image classification using MLP - Part II

Solving image classification using MLP - Part III

Getting Started with CNN

Why do we need CNN?

Introduction to RNN,LSTM and GRUs

Forward and backward propagation

Numpy from scratch

 Forward prop. using numpy

Backward prop. using numpy

Training model using numpy

Optimizers

SGD from scratch

RMSprop

Adam

NN on structured data

Loan prediction - preprocessing

Loan Prediction: Training and evaluating

Functional API in Keras for Deep Learning

Loan prediction using keras

Functional API _1

Functional_API_2

Getting started with images data

Reading and stacking images

Converting images into different formats

Extracting edges from images

Image classification using keras

neural networks in keras

Hyperparameter tuning

Improve your deep learning model

Early stopping
Dropout
Vanishing and Exploding gradient

Weight initialization

Batch Normalization

Image augmentation techniques

Image augmentation on Emergency data

Image augmentation, fit and generate

Model Checkpointing
Introduction to Convolutional Neural Network

and Implementation
Convolutional Neural Network in Keras

Hyperparameter Tuning for CNN in keras

Model Checkpointing in CNN

Introduction to Transfer Learning

 Solving the challenge using Transfer Learning

Transfer Learning: Using the architecture

of the pre-trained model

Transfer Learning: Freezing some layers and

training others

CNN Visualization

Working with text data

Regex in action
Regex in action: 2
Regex in action: 3

One-hot vector

Word embedding

Project - Building an Auto-Tagging System

Building auto tagging system

Advanced Sequence Models - LSTM & GRU

auto_tagging_system_LSTM
auto_tagging_system_GRU
auto_tagging_system_CNN

Project - Building an Auto-Tagging System

Building auto tagging system

 Web trafficing

web traffic forecasting 1

Project - Emergency vs Non Emergency

Vehicle Sound Classification

Emergency_and_Non_emergency_audio_classification

Unsupervised deep learning

photo_gallery_organization

Pytorch

CNN Improvements

Building an RNN model in PyTorch

Autoencoders in PyTorch

Transfer Learning in PyTorch

 Introduction to Natural Language
Processing (NLP)

Introduction to Natural Language Processing (NLP)

What is Natural language Processing (NLP)

Applications of NLP

Introduction to the course

Overview of this course

Setting up the system

Setting up the system (Text)

Text Processing: Handling text data

Reading Text Data

Regular Expressions in Python

Using Regular Expressions on Real-World Dataset

Text Pre-processing

Tokenization

stopword removal

normalization

Exploring text data

Information Extraction

Implementing POS
Implementing Dependency Parsing
Implementing NER

Implementing Rule Based Extraction

Project: UN Debate Analysis

String Similarity

Hamming distance
Levenshtein distance

Project Ranked Retrieval

Implementing Ranked Retrieval

Project: Next word Recommender System

Next word Recommender System

Project: Auto Correct

Building the autocorrect model

Feature Engineering for Text Data

Text Feature Engineering Implementation

Text Representation Implementation
Word Embeddings Implementation

Text Classification

Implementing SMS Spam detection

Project: Multi label Text Classification

Implementing Sentiment Analysis

Project: Multi label Text Classification

Auto tagging stack exchange questions

Unsupervised NLP - Topic Modeling

Implementing Topic Modeling

 Exploring Natural Language Processing
(NLP) using Deep Learning
Intro to NLP using Pytorch
Natural Language Processing using Deep Learning

Course Handouts

Setting up the System

Setting up the System (TEXT)

Getting Started with Google Colab (TEXT)

Recap of MLP and RNN

Recap of Multi Layer Perceptron

Quiz: Recap of Multi Layer Perceptron

Recap of RNN, LSTM and GRU

Quiz: Recap of RNN, LSTM and GRU

Recap: NLP Basics

Recap of NLP Basics

Neural Language Modeling

Challenges in N-Gram Language Modeling

Quiz: Challenges in N-Gram Language Modeling

Introduction to Neural Language Modeling

Quiz: Introduction to Neural Language Modeling

Project: Build an Auto-completion System (Text

Generation) using Neural Language Model

Understanding the Problem Statement: Text Generation

using Language Modeling

Quiz: Understanding the Problem Statement

Download Dataset

Loading the Dataset

Preprocessing and Exploring Text Data

Quiz: Preprocessing and Exploring Text Data

Data Preparation

Quiz: Data Preparation

Defining Model Architecture

Text Generation

Exercise: Things you can try out with Neural Language

Model

Assignment: Wikipedia Text Generation

Assignment: Wikipedia Text Generation

Sequence-to-Sequence Modeling
 Sequence-to-Sequence Modeling: Setting up Context

Quiz: Sequence-to-Sequence Modeling: Setting up

Context

Understanding Sequence-to-Sequence Modeling

Quiz: Understanding Sequence-to-Sequence Modeling

Architecture of Sequence-to-Sequence Model

Quiz: Architecture of Sequence-to-Sequence Model

Project - Text Summarization

Text Summarization

Transformer Models Basics

Introduction to Transformers

Quiz: Introduction to Transformers

Understanding Transformer Architecture

Quiz: Understanding Transformer Architecture

How Self-Attention is Computed

Quiz: Computation of self-attention

Understanding the BERT Model

Introduction to BERT

Quiz: Introduction to BERT

 Architecture of BERT
Quiz: Architecture of BERT

Pre-Training Tasks for BERT

Quiz: Pre-training Tasks for BERT

Project: Sentiment Analysis using BERT

Understanding the Problem Statement: Sentiment
Analysis using BERT

Quiz: Sentiment Analysis

Quiz: Sentiment Analysis

Setting up Colab Session and Installing Transformers

Library

Importing BERT pre-trained Model and BERT Tokenizer

Data Preparation

Model Building and Evaluation

Exercise: Things you can try out to fine-tune BERT

Assignment: Sentiment Analysis using BERT

Assignment: Sentiment Analysis using BERT

Project: Speech Command Identification

Project - Introduction to Speech Command Identification
Quiz: Project Introduction
 Implementation of Speech Command Identification using

CNN

Data Exploration

Load Data Using Custom Data Loader

Defining Model Architecture

Train the CNN Model for Speech Command Identification

Understanding Real - Time Audio Capture

Evaluation of Real -Time Speech Commands

Play 2048 using -Real-Time Speech Command

Identification

Assignment: Speech Command Identification for playing

Tic-Tac-Toe

Project: Build your first Chatbot

Introduction

About this module

Overview of Conversational Agents

Project - Foodbot

Overview of Rasa Framework

System Setup

Rasa NLU: Understanding user intent from a message

Rasa NLU: Extracting intents from a user's message

 Rasa Core: Making your chatbot conversational
Working with API

Implement Custom Action Service

Conversing with a Chatbot

Create a Workspace in Slack

Deploying to Slack

Assignment: Share your learning and build your profile

Shaping Tomorrow with

Generative AI
Contact us:

+91-9354711240

training_support@analyticsvidhya.com

analyticsvidhya.com/genaipinnacle