CLASS 11, 12Advanced LEVEL

Deep Learning & Generative AI

An advanced, applied course in Deep Learning and Generative AI for Class 11 students. Learners train CNNs using TensorFlow/Keras, apply transfer learning to custom datasets, understand LLM architecture, and build a Retrieval-Augmented Generation (RAG) demo — developing real, deployable AI skills.

Duration

10 Days

Total Hrs

26 Hours

Level

Advanced

What You'll Get

Expert Trainer-Led Sessions
Training Slides & Learning Materials
Practical Assignments
Assessment & Progress Report
Course Completion Certificate

Methodology

Instructor-Led Training
Practical Hands-on Sessions
Live Demonstrations
Mini Assignments & Assessments
Project-Based Learning

Detailed Syllabus

Practical, engaging and concept-based learning

1

Deep Learning with TensorFlow/Keras

Topics Covered

Building neural networks with TensorFlow/Keras
CNNs for image classification — hands-on
RNNs/LSTMs for sequence data — conceptual + basic code

Practical / Activities

Train a CNN image classifier on a sample dataset

Outcomes

Build and train deep learning models using TensorFlow/Keras

2

Transfer Learning in Practice

Topics Covered

Ready to start?

₹499

One-time Enrollment Fee

Enroll Now

Course Snapshot

Course Code
LEQ-C11-DL-GENAI
Grade Level
Class 11, 12

Prerequisites

Python programming proficiency

Enroll Now

What is transfer learning and why it matters
Fine-tuning pretrained models
Applying transfer learning to custom datasets

Practical / Activities

Apply transfer learning to classify a custom dataset

Outcomes

Apply transfer learning for practical tasks

3

Understanding LLMs & Advanced Prompting

Topics Covered

LLM architecture — conceptual overview (transformers)
Advanced prompt engineering & prompt chaining
Using GenAI APIs (OpenAI, Gemini, Claude) in code

Practical / Activities

Build a GenAI-powered Q&A tool using an API

Outcomes

Integrate GenAI APIs into applications
Apply prompt chaining techniques

4

Retrieval-Augmented Generation (RAG)

Topics Covered

What is RAG and why it's used
Basic RAG pipeline: documents, retrieval, generation

Practical / Activities

Build a simple RAG demo using a small document set

Outcomes

Understand RAG and its applications
Build a working RAG demo

Class 10 DL/GenAI course or equivalent experience

Objectives

Build and train neural networks using TensorFlow/Keras
Apply transfer learning to custom datasets
Understand LLM architecture at a conceptual level
Build a simple Retrieval-Augmented Generation (RAG) application