Machine Learning,
AI & GenAI

✦Gen AI Ready

A 7-week deep dive — from classical ML and deep learning to transformers, diffusion models, and building AI agents. Theory meets hands-on projects at every step.

7 Weeks

Duration

Intermediate+

Level

Live

Sessions

Enroll Now Free Demo Class
Live Cohort

ML, AI with GenAI

₹4,00038% OFF
₹2,499

Enroll Now

Course Overview

A structured 7-week programme covering Machine Learning, Deep Learning, and Generative AI.

What You'll Learn

  • Linear Algebra, Statistics & ML Foundations
  • Supervised & Unsupervised Learning (SVM, K-Means, Decision Trees)
  • Deep Learning (CNNs, RNNs, LSTMs, Backpropagation)
  • Transformers & Self-Attention Mechanisms
  • Prompt Engineering & RAG Pipelines
  • Diffusion Models, Vision Transformers & AI Agents

What You'll Achieve

  • Build & deploy ML models end to end
  • Design deep learning architectures from scratch
  • Create RAG pipelines & fine-tune LLMs
  • Build a capstone AI agent system

Why choose this track?

Everything you need to break into ML, AI, and Generative AI.

Continuous Assignments
Doubt clearing sessions
Mock interviews
3 Real-world projects

Course Curriculum

A weekly roadmap — from ML foundations and deep learning to transformers, GenAI, and building AI agents.

  • Vectors, dot product & cross product
  • Matrix operations & transformations
  • Probability distributions & inferential statistics
  • Cost function & gradient descent
  • Linear Regression — line fitting & model evaluation (MSE, R²)
  • Feature scaling & normalization
  • Support Vector Machines — hyperplane, margin & kernel trick
  • K-Means clustering — centroid migration & elbow method
  • Decision Trees — entropy, information gain & Gini impurity
  • Random Forests & ensemble methods
  • Dimensionality Reduction — PCA, eigenvectors & eigenvalues
  • Validation — K-Fold cross-validation & bias-variance trade-off
  • AI ethics, fairness & responsible ML
  • Perceptron & multi-layer architecture (MLP)
  • Activation functions (ReLU, sigmoid, tanh)
  • Forward propagation & loss functions
  • Backpropagation — chain rule & computational graphs
  • SGD, momentum & learning rate schedules
  • Adam optimizer — intuition & math
  • Dropout & batch normalization
  • Convolution, kernels & feature maps
  • Pooling, stride & padding
  • CNN architectures (LeNet, VGG, ResNet)
  • Image classification project
  • Recurrent Neural Networks — hidden state & vanishing gradients
  • Gated Recurrent Units (GRU)
  • LSTMs — forget, input & output gates
  • Time-series forecasting project
  • Attention mechanism — Query, Key, Value
  • Multi-head attention & positional encoding
  • Transformer architecture (encoder-decoder)
  • Vision Transformers (ViT) — image patches as tokens
  • Comparing ViT vs CNN performance
  • Transfer learning with pre-trained models
  • Zero-shot & few-shot prompting
  • Chain-of-thought reasoning & prompt patterns
  • Retrieval-Augmented Generation (RAG)
  • Vector databases & embeddings
  • Fine-tuning vs in-context learning
  • Forward & reverse diffusion — denoising
  • U-Net architecture & Stable Diffusion
  • Agent architecture — planning & tool use
  • Building sub-agents (search, code, write)
  • Orchestration & feedback loops
  • End-to-end RAG pipeline project
  • 🚀 Final Project: Build & deploy a complete AI agent system
  • 🔧 Bonus: Git, GitHub & portfolio deployment
←View All Courses
ML, AI with GenAI7 Weeks

Starting at ₹4,000₹2,499