While many programs teach you about AI, the upGrad Advanced Certificate Program teaches you how to be at the forefront of this emerging technology by building Generative AI applications. Join this 4 month project based learning program and walk away with the ability to deploy your own tools. Upskill now to stay ahead of the AIvolution.
This program is offered in partnership with upGrad, a global leader in higher online education with 2 million learners across 100 countries worldwide. With the latest technology, pedagogy, industry partners and world-class faculty, upGrad creates immersive online learning experiences for learners globally.
Complete all the courses successfully to obtain this recognition
- Become the most desirable candidate for the most in-demand jobs.
- Unlock upGrad status
- Curriculum designed by AI experts
STUDY MODEL
Online, 120 hours of learning
ACCREDITATION
upGrad Institute Singapore
DURATION
ELIGIBILITY
Basic programming proficiency
FEES
USD 2,500
VALUE-ADD
Gen AI masterclasses by industry experts
- Introduction to Python and Programming
- Python Data Types, Variables, Operators, Data Structures
- Python Programming Constructs: Conditionals, Loops, Functions
- UDFs, Best Coding Practices and Exception Handling
- Python for Data Science and Pandas: Working with relational databases, Data Cleaning, Preprocessing, Analysis
- Advanced Text Processing using Pandas
- Basics of Linux: Commands, Setting up Local Environment
- Define the different components of the bot and design the workflow for creating the bot
- Apply prompting techniques to create prompts for asking questions and evaluating the customer’s response
- Prompt Engineering: Improve the assistant’s responses by applying simple (non-reasoning) prompting techniques
- Prompt Engineering: Improve the assistant’s accuracy by applying Chain of Thought reasoning-based prompting techniques
- Apply fine-tuning using OpenAI APIs to train an LLM on your custom data
- Integrate speech input using OpenAI’s Whisper API
- Deploy and launch ShopAssistAI application on Flask/Gradio
- Iterate and improve the UI of the app using ChatGPT’s code writing capabilities
- Understand the working of multimodal models like Stable Diffusion: Denoising, Diffusion, Autoencoders, Contrastive Learning, Shared Embedding Spaces
- Apply image prompting techniques on Dall-E and Midjourney to generate desired product images using various stable diffusion methods and prompt parameters such as style, ratios, seeds, FPS
- Understand and apply the fundamentals of style, design and photography to improve image quality and accuracy with prompt iteration and few-shot prompting
- Apply self-consistency, seeding and standardised formatting in prompting to create consistent styles and designs across hundreds of product images
- Understand prompting for code generation and generate accurate codes for data science tasks in a larger ML problem using GPT and Copilot
- Read, load and embed large datasets and tables to read your data with GPT/Copilot
- Perform data cleaning and analysis by both generating code & writing direct prompts to GPT
- Write prompts for data analysis tasks and insights in accordance to the business problem and objectives
- Perform semi-automated modelling, fine-tuning and evaluation for various regression, classification and clustering problems
- Define the components of Chatbot
- Understand when to use embedding over fine tuning
- Understand the working of embeddings and how they help in semantic search
- Create and analyse embeddings for semantic search
- Create embeddings for large documents by creating chunks
- Create a Q/A system that fetches answer using similarilty search over embeddings
- Scale the Q/A system by making use of vectorstores like Pinecone
- Embed, index large documents and search in Vectorstore
- Integrate LLM chat models over the searched embeddings to respond to the customer
- Experiment with different vectorstores, search and index algorithms and LLMs to improve the chatbot
- Define the components of the knowledge retrieval system and design the workflow
- Explore how LangChain can connect the different components of the system
- Understand the different parts of LangChain – Models, Prompts, Indexes, Chains, Memory and Agents
- Explore the different tools in LangChain and initialise an agent that uses the tools to read different types of files or data present in the company database
- Build the backend for the system using Vectorstore options present in LangChain
- Divide the documents into chunks and apply the LLM to create the embeddings and extract entity for the chunks of document and store them in the Vectorstore
- Construct the Search Index and Entity Store and create a functionality to update it with every question that the user asks
- Use the Chain functionality of LangChain to connect all the components
- Evaluate the results and improve them by experimenting with different LLMs, indexing and embedding algorithms
- Explore other agents and tools to improve the system like adding features like automatic email notifications on some issues, etc.
- Explore the Generative AI services offered by Azure: Azure OpenAI services
- Modify the workflow design of knowledge retrieval system for scalability
- Identify the Azure services required for creating the scalable system
- Expose the system through a chat based front end to the user
- Mitigating risks in AI: Responsible AI
- RLHF as a Product to train your own LLM
- Multimodal Learning: Audio, Image, Text, Heatmap among others within a LLM
