Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study, Virtual Classroom, Campus Based/Physical Classroom | Video and Text Based |
Course Overview
The advanced certification course supports the students in building and deploying GenAI models. The course offers hands-on project-based learning with 25+ projects. The course offers a cutting-edge Generative AI curriculum that is co-designed with the IIT Guwahati.
The students will gain in-depth knowledge of the concepts of LLMs and RAGs to develop and deploy RAGs and Agentic systems. The Applied Generative AI Course certification by OdinSchool offers hackathons, case study discussions, and Q&A sessions with experts. With the help of industry experts, they will apply the learned concepts in real-world scenarios.
Also Read: Online Artificial Intelligence Courses & Certifications
The Highlights
- Live Online Classes
- Live Doubt Clearing Sessions
- Professional Profile Building
- Workplace Behavioral Skills Workshops
- Campus Immersion Programme
- Advanced Certification from E&ICT/IIT Guwahati
Programme Offerings
- interview preparation
- Placement Support
- Executive Alumni Status at E&ICT Academy
- IIT G 200+ Hours of Interactive Sessions by Experts & IIT Faculty
- Career Guidance
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | IIT Guwahati (IITG) |
Applied Generative AI Course Fee Structure
Certification Course | Fees |
Applied Generative AI Course | Rs 1,25,000+GST |
Eligibility Criteria
Academic Qualifications
The aspirants must have a bachelor's degree with an aggregate of at least 50% marks and with a background in Mathematics or Computer Science, and knowledge of Descriptive Statistics, Linear Algebra, SQL, and Python are preferable.
Certification Qualifying Details
Upon the completion of the course, the students will receive an advanced Certification from E&ICT Academy, IIT Guwahati.
What you will learn
After completing the Applied Generative AI Course certification syllabus, the participants learn technologies and tools to develop and deploy GenAI models. They will gain in-depth knowledge of Python advanced, exploratory data analysis (EDA) and foundational language models, and fine-tuning. With the support of industry professionals aspirants will be able to apply the concepts in real-world applications.
The aspirants will gain a deep understanding of Deep Learning (DL) and Natural Language Processing (NLP), RAGs, agents, vision and deployment. Upon the completion of the Applied Generative AI Course training, they will gain hands-on real-world projects like Chat with Website, Medical Chatbot, Text to SQL Query and Output Generator and Q&A with a Code Base.
Who it is for
The certificate course is designed for aspiring students, and working professionals to develop their skills and knowledge. This course is also beneficial for:
- Data Scientist
- Machine Learning Engineer
- Artificial Intelligence Engineer
- Software Developer - Gen AI
Admission Details
Students can join the Applied Generative AI Course classes by following the below-mentioned steps:
Step 1: Browse the link mentioned below:
https://www.odinschool.com/generative-ai-course-iitg
Step 2: Candidates can visit the course page mentioned above, click on “Apply Now,” add the required information and submit.
Step 3: Talk with the counsellor, review your eligibility, and begin the course.
Application Details
Candidates can visit the official course page and click on “Apply Now,” fill out the necessary details in the form and submit it.
The Syllabus
Orientation
- Introduction to curriculum & program structure
- A walk-through of LMS & Odin Labs
- A walk-through of a GenAI product and the engineering behind
Python Advanced
- Recursion
- Lambda Functions
- Higher Order Functions
- Numpy
- Pandas
- Date-time
- Regular Expression
- OOPs- class, Object, Principles of OOPS
- Decorators, Exception Handling, File Handling, Generators
Exploratory Data Analysis (EDA)
- Data pre-processing and exploration
- Handling missing values
- Handling outliers
- Dealing with categorical variables
- Introduction to Machine Learning and SKlearn
- Handle Date columns and column with multiple values
- Feature Scaling
- Covariance & Corelation
- EDA with Student data
Deep Learning and Natural Language Processing
- Perceptron in-depth intuition and implementation
- Multi-layer perceptron(ANN-Artificial Neural Network)
- Recurrent Neural Network (RNN) and its types
- Introduction to NTLK, spacy libraries
- Tokenization
- Word embeddings
- Small project to create word embeddings
Foundational Language Models, Finetuning
- Foundational Language Models
- LLAMA3 Instruct 8B / 70B
- LLAMA3 Chat - LLAMA3 code
- E5 embedding
- MIXTRAL 8X7B
- Small Language Models (SLMs) (PHI3, bitNet B1.58)
- Planning & Reasoning
- Transformer Architecture
- Types of Attention
- Types of positional embedding
- Long context
- Enhancing LLM throughput on GPUs
- KV (Key Value) Cache
- Flash attention
- VLLM (Virtual Large Language Model)
- TRT LLM (TensorRT Large Language Model)
- Input / Op token length
- Tokenization strategies
- Long rope
- Para Efficient Fine tun Low Rank Adaptation (LORA), P tuning, finetuning of embedding models)
Mini Capstone Project
Retrieval Augmented Generation (RAGs)
- Alignment
- RLHF (Reinforcement Learning from Human Feedback)
- DPO (Direct Preference Optimization)
- RPO (Reasoning Preference Optimization)
- RAGs (Retrieval Augmented Generation)
- Advanced ingestion
- Chunking
- Embedding
- Search
- Ranking
- Generation
- Evaluation
- RAG frameworks
- LLANGCHAIN basics
- LLAMAINDEX
- LLANGRAPH
Agents, Vision, Deployment
- Agentic workflows and function calling
- LLANGCHAIN advanced
- AUTOGEN
- Generative AI for Images and videos
- CLIP (Contrastive Language-Image Pre-training)
- UNETS (U-shaped encoder-decoder network architecture)
- Diffusion models
- Containerised deployment and Kubernetes - LLM deployment