Duration: 5 days – 35 hrs
Overview
This course is designed to equip developers with the skills and knowledge required to leverage generative AI technologies in their applications. It covers the fundamentals of generative AI, key algorithms and models, practical implementation techniques, and ethical considerations. By the end of this course, participants will be able to create, implement, and optimize generative AI models for various use cases.
Objectives
• Understand the fundamentals of generative AI and its applications.
• Learn about key generative AI models, including GANs, VAEs, and transformer-based models.
• Gain hands-on experience with popular generative AI frameworks and tools.
• Develop and deploy generative AI models for real-world applications.
• Address ethical considerations and challenges in generative AI.
Audience
- Software Developers and Engineers: Individuals with programming experience who are looking to integrate generative AI capabilities into their applications.
- Developers are interested in enhancing their skill set with advanced AI techniques.
- Data Scientists and Machine Learning Practitioners: Professionals already working with data and machine learning who want to expand their expertise to include generative models.
- Those involved in creating predictive models who wish to explore generative approaches for data augmentation and more.
- AI Enthusiasts and Researchers: Individuals with a strong interest in artificial intelligence and machine learning who want to delve into generative AI.
- Researchers exploring new frontiers in AI who wish to understand the practical aspects of implementing generative models.
- Graduate Students in AI and Related Fields: Students pursuing degrees in computer science, data science, or related fields looking to gain practical knowledge and hands-on experience in generative AI.
- Product Managers and Technical Leads: Professionals responsible for guiding AI-driven product development who need to understand the capabilities and limitations of generative AI.
- Technical leads who aim to incorporate generative AI into their team’s projects.
- AI Startup Founders and Innovators: Entrepreneurs in the AI space seeking to leverage generative models for innovative products and solutions.
- Innovators looking to create new applications and services based on generative AI technologies.
Prerequisites
• Proficiency in Python.
• Understanding of basic machine learning concepts and algorithms.
• Basic knowledge of neural networks and deep learning frameworks (e.g., TensorFlow, PyTorch) is helpful but not mandatory.
Course Content
Day 1 – Python
▪ Python Concepts
▪ Python Operators
▪ Python Data Types
▪ Python List
▪ Python Tuples
▪ Python Dictionary
▪ Python File Handling
▪ Python Functions
▪ Python Variables
Day 2 – Machine Learning
▪ ML Foundation
▪ Resource Guide
▪ ML Concepts
▪ Numpy
▪ Pandas
▪ Numpy and Pandas
▪ Supervised Learning
▪ Unsupervised Learning
▪ Linear regression
Day 3 – Generative AI Foundation
▪ GenAI Course Overview
▪ Define GenAI
▪ GenAI Demo
▪ Lab: Generate-Videos-in-single-prompt
▪ Applications of GenAI
▪ Technologies behind GenAI
▪ Part1-Ethics and Legal in AI
▪ Part2-Ethics and Legal in AI
▪ Lab: Generate PPT in 30 secs
▪ Managing GenAI Projects
▪ Security in GenAI
▪ Future of AI
▪ Lab: Generate AI voice in a single prompt
▪ GenAI in Finance
▪ GenAI in Sales and Marketing
▪ GenAI in HR Management
▪ Lab: Generate AI avatar videos
▪ GenAI in Healthcare
Module 2: Prompt Engineering
▪ Define Prompt Engineering
▪ Prompting Technique
▪ Behind the scenes Prompt to output
▪ Lab: Prompt with ChatGPT 3.5
▪ Lab: Prompt with ChatGPT 4.0
▪ Lab: Part1-Prompt with Anthropic claude
▪ Lab: Prompt with Google Gemini
Module 3: Natural Language Processing
▪ Introduction to NLP
▪ Applications of NLP
▪ Evolution of NLP
▪ Challenges in NLP
▪ NLP tasks
▪ NLP Pipeline
▪ NLP tools and Libraries
▪ Lab 1: Email spam filtering
▪ Lab 2: Text summarization
▪ Lab 3: NLP-data-pre-processing
Day 4 – Dive into LLM
▪ Introduction to LLM
▪ Applications of LLM
▪ Advantages of LLM
▪ Custom vs FineTune LLM
▪ Multimodal LLM
▪ Lab: Access OpenAI programmatically
▪ Lab: OpenAI LLM – NLP Tasks
▪ Lab: Access Anthropic Claude Programmatically
▪ Lab: Claude LLM – NLP Tasks
Module 5: Developing Generative AI Applications
▪ Lab: Develop PDF chatbot
▪ Lab: Develop Text & AI voice-integrated GenAI Apps
▪ Lab: Develop a Chatbot for website PHI data
Day 5 – Langchain
▪ Introduction to Langchain
▪ Overview of Langchain Architecture
▪ Use Cases of Langchain
▪ Integrating Langchain with Existing Systems
▪ Lab: Setting Up Langchain Environment
▪ Lab: Basic Langchain Operations and Commands
Module 8: Developing Applications with Langchain
▪ Lab: Build a Simple Chatbot Using Langchain
▪ Lab: Langchain with Google search Integration
Module 9: Public Cloud GenAI Solution Demo
▪ Introduction to AWS Bedrock
• Demo – AWS bedrock demo by trainer
▪ Introduction to Google Vertex AI
• Demo – Google Vertex AI demo by trainer
▪ Introduction to Azure AI studio
• Demo – Azure AI studio demo by trainer
