Artificial Intelligence(AI) with Industry oriented use cases

About Course

This 8-week course on industry-oriented AI provides solid foundation for developing AI-based applications. We will start with general software Engineering Concepts in an agile way with hands-on exercises on the tool JIRA. We will give the intrdouction to AI concepts and deep dive into Generative AI models, Building blocks of AI framework and Significance of Generative AI in different domains. We will discuss Large Language Models(LLM) and integration of LLM with Gen AI. We will show the CHATGPT and prompt Engineering in GPT. We will also discuss how to use the gen AI tools (GAN and VAE).

This course deep dives into Deep Learning, having the following:

Tensor Flow
PyTorch
Keras
CNN and RNN
Concepts
Technical Deep dive
Code Examples
Case Studies

We will also discuss the visualization tools like Matplotlib and Python. This course covers how to use Python for architecting and developing AI applications.

Natural Language Processing(NLP) is covered using tools.

We will also cover Retrieval Augmented Generators(RAG) and Langchian and how to develop machine Learning algorithms.

Agentic AI and how to develop agents in different domains will be part of the curriculum. one of the important topics includes ‘How to create the AI center of Excellence(AI COE) in Insurance and Healthcare domains is part of this course.

All the topics will have industry use cases, user stories, architecture and the corresponding Python code with expected outputs.will also showcase the testing strategy and relevant test cases to test these applications.

This course also touches Quantum computing the intercation of AI and Quantum computing.

All the topics will have assignments and hands-on coding and quizs focusing on Banking, financial services and Insurance (BFSI) and Healthcare domains. We will use the software engineering best practices, processes and tools to develop and deploy these applications.

This 8 week course on AI using industry use cases enable the participants to understand the use cases in different domains like Banking, financial services ans insurance(BFSI) and healthcare (HC),architect the AI solutions using different tools and technologies pertaining to AI and ML,develop various models and algorithms ,evaluate and and deploy them. this course allows the participants to work on real time applications in these domains. Make the participants ready for the industry and as the emphasis is on developing the applications using Python , this course enables them to be ready for AI based architects and developers.

Course Content

Module 1 : General Software Engineering Concepts
It covers - Agile software Development - JIRA - Agile KPIs - Security in Software Applications - Software configuration Management(GITHUB) - DevOps

Introduction to agile methodology
Agile process framework & User story creation
Sprint Planning and SCRUM
QUIZ 1

Module 2 : Introduction to AI and Generative AI
Covers the following: 1 Concepts 2 Technical Deep dive 3 Code Examples 4 Case Studies(Spam Email) 5 Assignments and Quiz 6 Significance of Generative AI in different domains 7 10 things we should know about Generative AI 8 Generative AI models 9 Building blocks of AI framework

Module 3 : Generative AI and CHATGPT
1. Generative AI and LLM Integration 2. CHATGPT 3. Prompt Engineering in Generative AI 4. Generative AI Tools a. GAN and VAE

Module 4 : Deep Learning
Covers the following: a. Tensor Flow b. PyTorch c. Keras d. CNN and RNN e. Concepts f. Technical Deep dive g. Code Examples h. Case Studies i. Assignments and Quiz

Module 5 : Visualization Tools (copy)
a. Matplotlib

Module 6 : Python and AI
Developing Aplications in Python with rich set of libaries

Module 7 : Natural Language Processing
a. Concepts b. Technical Deep dive c. Tools i. NLKT ii. SpaCy iii. Hugging Face Transformers d. Code Examples e. Case Studies f. Assignments and Quiz

Module 8 : SVM
a. Concepts b. Technical Deep dive c. Code Examples d. Case Studies e. Assignments and Quiz

Module 9 : Retrieval-Augmented Generation(RAG)
a. Concepts b. Technical Deep dive c. lLamaIndex d. Code Examples e. Case Studies f. Assignments and Quiz

Module 10 : Machine Learning
a. Supervised and Unsupervised b. Machine learning algorithms i. Concepts ii. Technical Deep dive iii. Code Examples iv. Case Studies v. Assignments and Quiz

Module 11 : Agentic AI
a. AI Agents, Security & Capstone b. CrewAI, LangGraph, agent orchestration and evaluation

Module 12 : AI Center of Excellence(AI COE)
How to set up AI COE - Processes - Tools and Technologies

Domains Covered
Banking, Financial Services ans Insurance(BFSI) - Insurance Premium -RIsk modelling in Banking -Portfolio allocation in Financial services - Influence of age on the investor decisions -Stock prediction - Algorthimic trading -Invoice Processing Healthcare(HC) Claims prediction Diabetis prediction Lung cancer prediction Risk of redmission in the hospitals AI in Quality Engineering with Risk based testing(RBT) Email spam detection

Combined quiz and Assessment on Visulaization tools(Matplotlib),PYTHON,Natural language processing(NLP),Support vector machines(SVM),Retrieval augmented generation(RAG) ,Machine Leaning(ML), Agentic AI, AI center of excellence(AI COE) and domains covered

Student Ratings & Reviews

No Review Yet

About Course

What Will You Learn?

Course Content

Module 1 : General Software Engineering Concepts It covers - Agile software Development - JIRA - Agile KPIs - Security in Software Applications - Software configuration Management(GITHUB) - DevOps

Introduction to agile methodology

Agile process framework & User story creation

Sprint Planning and SCRUM

QUIZ 1

Introduction Artificial Intelligence(AI) and Generative AI

AI in a Nutshell

Introductioon to AI and Generative AI

Module 3 : Generative AI and CHATGPT 1. Generative AI and LLM Integration 2. CHATGPT 3. Prompt Engineering in Generative AI 4. Generative AI Tools a. GAN and VAE

Building blocks of AI framework

Large Language Models(LLM) , GPT and Prompt Engineering

Generative Adversarial Networks (GANs) & Variational Autoencoders (VAEs)

Short answer quiz on Generative AI CHATGPT

Module 4 : Deep Learning Covers the following: a. Tensor Flow b. PyTorch c. Keras d. CNN and RNN e. Concepts f. Technical Deep dive g. Code Examples h. Case Studies i. Assignments and Quiz

Deep Learning

Case Study-Predicting the Heart failure with Artificial Neural networks

Tensor Flow

Keras

CNNs: Convolutional Neural Networks.RNNs: Recurrent Neural Networks .

Deep Learning, TensorFlow, and Keras Quiz

Module 5 : Visualization Tools (copy) a. Matplotlib

AI Visualization tools -Matplotlib

Module 6 : Python and AI Developing Aplications in Python with rich set of libaries

PYTHON AND AI

Module 7 : Natural Language Processing a. Concepts b. Technical Deep dive c. Tools i. NLKT ii. SpaCy iii. Hugging Face Transformers d. Code Examples e. Case Studies f. Assignments and Quiz

NLP-Concepts,tools and use cases

NLP tools

NLP case studies in Healthcare and other domains

Module 8 : SVM a. Concepts b. Technical Deep dive c. Code Examples d. Case Studies e. Assignments and Quiz

Support Vector Machines(SVM)

Module 9 : Retrieval-Augmented Generation(RAG) a. Concepts b. Technical Deep dive c. lLamaIndex d. Code Examples e. Case Studies f. Assignments and Quiz

Retrieval Augemented Generation(RAG)-Concepts,Llama Index,case study and Architecture

Module 10 : Machine Learning a. Supervised and Unsupervised b. Machine learning algorithms i. Concepts ii. Technical Deep dive iii. Code Examples iv. Case Studies v. Assignments and Quiz

Machine Learning

Module 11 : Agentic AI a. AI Agents, Security & Capstone b. CrewAI, LangGraph, agent orchestration and evaluation

Agentic AI-Concepts

Agentic AI examples

Agentic AI components and Layers

Agentic AI and RAG

Agentic AI RAG Workflow

Module 12 : AI Center of Excellence(AI COE) How to set up AI COE - Processes - Tools and Technologies

Setting up of AI center of Excellence(AI COE)

Banking, Financial services and Insurance(BFSI) and Healthcare domains are covered for use cases purpose.with use cases pertinent to these domains.