AI Summer Bootcamp 2025
Master AI & Machine Learning in just 6 weeks with live projects and expert mentorship!
Duration 6 Weeks, 60 hours
Medium Live Online
Language Hindi, English
Fee Rs. 8999/-
Batches
  • 9 June 2025, 1:00 PM - 3:00 PM, Mon - Fri
  • 15 June 2025, 3:30 PM - 5:30 PM, Mon-Fri
Instructors
  • Amit Saini
    Amit Saini
    Co-Founder & CEO : Wayo Robotics Chief Mentor : Wayo Labs
    linkedin
  • Kuldeep Pandey
    Kuldeep Pandey
    Co-Founder & CTO : Wayo Robotics Chief Mentor : Wayo Labs
    linkedin
  • 🧑‍🏫Live Interactive Classes
  • 📚 Beginner-Friendly Curriculum
  • 💻 Hands-on Coding Sessions
  • 🎓 Certificate of Completion
  • 🛠️ Multiple Projects & Real-World Case Studies
Tools & Technologies You'll Work With
Python for AIPython for AI
PyTorchPyTorch
SeabornSeaborn
Scikit LearnScikit Learn
PandasPandas
MatplotlibMatplotlib
NumpyNumpy
Jupyter NotebookJupyter Notebook
Course Highlights
Foundations of AI/ML
📘 Introduction to AI/ML
  • 🔍 What is AI and Machine Learning?
  • 📊 Types of Machine Learning (Supervised, Unsupervised, Reinforcement)
  • 🌐 Real-World Use Cases
  • 🧠 Introductory Theory and Concepts
  • 🛠️ Tools Setup
  • 🐍 Python Recap Sessions
Python for AI – Practice Sessions
  • Variables, Loops, Functions
  • Working with Data Structures (Lists, Tuples, Dictionaries)
  • File Handling and Libraries Overview
  • Practice Notebooks for In-Class Coding
Math for ML – Vectors, Matrices & NumPy
  • Basics of Linear Algebra
  • Vectors, Matrices, and Matrix Operations
  • NumPy Arrays and Broadcasting
  • Hands-on Code Examples using NumPy
Data Manipulation with Pandas
  • Series and DataFrames
  • Reading & Writing CSV/Excel Files
  • Data Cleaning, Filtering, Grouping
  • Practical Exercises with Pandas
Data Visualization with Matplotlib
  • Line, Bar, Scatter, Histogram Charts
  • Customizing Graphs (Labels, Legends, Colors)
  • Building Visual Dashboards in Notebooks
  • Practical Exercises with Matplotlib
Math Refresher
Calculus, Probability & Statistics
  • 🔢 Introduction to Calculus for ML
  • 🎲 Probability Basics
  • 📈 Statistics for Data Analysis
  • 📝 Assignments: Problem sets and concept-building worksheets
Supervised Learning
Linear Regression
  • 🧮 Simple Linear Regression: Theory and implementation
  • 📉 Multivariate Linear Regression
  • 🧪 Hands-on using Scikit-Learn
  • ✅ Model evaluation: MSE, RMSE, R² Score
  • 📝 Working on Use cases
Beyond Linear – Polynomial & Logistic Regression
  • 🌀 Polynomial Regression: When linear isn’t enough
  • 📈 Logistic Regression: Classification vs Regression
  • ⚙️ Gradient Descent: Cost function minimization (with visuals)
  • 🧪 Implement from scratch and using libraries
K-NN and Model Evaluation
  • 📍 K-Nearest Neighbors (K-NN): Theory, Euclidean distance, choosing 'k'
  • 🧮 Evaluation Metrics for Classification
  • ⚙️ Accuracy, Precision, Recall, F1 Score
  • 🧪 Confusion Matrix and Cross Validation in action
Mini Project – Predict & Evaluate
  • Apply concepts learned through a guided mini-project
  • Evaluate model performance using key metrics
  • Tackle real datasets using Scikit-Learn
  • Bridge theory and practice confidently
Data Preprocessing, Decision Trees, and Model Tuning
Data Preprocessing & Feature Engineering
  • 🧼 Foundation for building quality models through better data pipelines
  • 🔍 Handling Missing Data (mean, median, mode, interpolation)
  • 🔠 Encoding Categorical Data: Label encoding & One-hot encoding
  • ⚖️ Feature Scaling: Standardization, Normalization
  • 🧩 Feature Engineering Basics
Decision Trees & Entropy
  • 🌲 How Decision Trees Work: Splits, Gini Index, Entropy
  • 🧠 Overfitting & Pruning
  • 🧪 Build Decision Trees from scratch and using Scikit-Learn
  • 🧬 Feature Importance & Tree Visualization
  • 🧩 Working on real use case
Random Forests & Ensemble Methods
  • Random Forest Classifier: Bagging and bootstrapping
  • Model training and testing with Sklearn
  • Ensemble Techniques Overview: Bagging vs Boosting
  • Evaluate model using Confusion Matrix & ROC Curve
  • Working on real use case
Hyperparameter Tuning & Cross Validation
  • Manual Parameter Tuning
  • Grid Search & Random Search using GridSearchCV
  • K-Fold Cross Validation
  • Practical lab: Improve a model using tuning techniques
  • Mini Project - Working on real use case
Unsupervised Learning & Dimensionality Reduction
Introduction to Unsupervised Learning
  • 📖 What is Unsupervised Learning?
  • 🧠 Key differences between supervised & unsupervised approaches
  • 🧬 Applications: Customer segmentation, anomaly detection, topic modeling
  • ✨ Overview of Clustering and Dimensionality Reduction
  • 🧪 Hands-on: Explore a raw dataset and brainstorm potential groupings
K-Means Clustering
  • 🎯 K-Means Algorithm: Concept, Objective Function, Iterative Optimization
  • 📐 Choosing ‘k’: Elbow Method and Silhouette Score
  • 🧪 Hands-on Implementation with Sklearn
  • 🧬 Cluster visualization with Matplotlib & Seaborn
  • 🧪 Hands-on: Customer Segmentation(e.g. e-commerce or banking datasets)
Hierarchical Clustering & DBSCAN
  • 🌌 Agglomerative Hierarchical Clustering - Dendrograms, linkage types, distance metrics
  • 🌪️ DBSCAN (Density-Based Clustering)
  • 🧪 Handling outliers and irregular cluster shapes
  • 🧪 Visualizing clusters and comparing with K-Means
  • 🧪 Hands-on: Working on Use Case
Dimensionality Reduction with PCA & t-SNE
  • 🧮 PCA (Principal Component Analysis)
  • 🌪️ Intuition, eigenvectors/eigenvalues, explained variance
  • 🧪 Hands-on with 2D/3D PCA visualizations
  • 🌌 t-SNE for non-linear dimensionality reduction
  • 🧪 Reduce a high-dimensional dataset and visualize clusters
  • Mini Project – Unsupervised Analysis
Deep Learning with PyTorch
Introduction to Neural Networks
  • 🧠 What is a Neural Network? (biological vs artificial)
  • 🔗 Structure: Neurons, Layers, Weights, Activation Functions
  • 📉 Forward Propagation & Loss Functions (conceptual)
  • 🔁 Backpropagation: How learning happens
  • ✏️ Activation Functions: Sigmoid, ReLU, Softmax
Build a Feedforward Neural Network in PyTorch
  • 🗂️ Load MNIST dataset using torchvision
  • 🔧 Model Building using nn.Module and Sequential
  • 🔁 Training loop: forward pass, loss, backprop, optimization
  • 📉 Visualize training loss and accuracy
  • 🧪 Evaluate on test set
  • 🤖 Hands-on: Build and train a digit classifier using a 2-layer NN
CNNs for Image Classification
  • 🧱 Why use CNNs: local patterns, parameter efficiency
  • 🔍 Layers : Conv2D, MaxPool2D, Flatten, FullyConnected
  • 🏗️ Build a simple CNN using PyTorch
  • 🖼️ Train on Fashion-MNIST or CIFAR-10 (subset)
  • 📊 Evaluate and visualize predictions
  • 📊 CNN architecture visualization with filter maps
Recurrent Neural Networks(RNN) & NLP
  • 🧱 RNNs, LSTMs, GRUs
  • 🔍 Tokenization, padding, embedding
  • 🏗️ Text classification
  • 🖼️ Sequence generation
  • 📊 Train an LSTM or GRU for sentence classification
  • 📊 Sentiment Analysis Project
  • Deep Learning Project – Capstone Project
Large Language Models
Introduction to Large Language Models (LLMs)
  • 🧱 What are LLMs? (Transformers, attention mechanism)
  • 🔍 Difference between LSTM vs Transformer
  • 🏗️ Pretraining vs Fine-tuning
  • 🖼️ Prompt engineering basics
  • 📊 Hugging Face Transformers ecosystem
  • 📊 LLaMA vs GPT vs BERT
Frequently Asked Questions

This program is designed for engineering students, graduates, and anyone with a basic understanding of programming who wants to learn Artificial Intelligence and Machine Learning from scratch.

It’s a 6-week live online course, with 5 sessions per week, each lasting approximately 2 hours...

Basic knowledge of Python programming and mathematics (linear algebra, probability, and statistics) is recommended but not mandatory. We will provide introductory sessions to bring everyone up to speed.

The training will be a mix of live online sessions, hands-on coding labs, assignments, and project work.

Yes, on successful completion of the program and projects, you will receive a certificate of completion from Wayo Labs.

You can enroll by clicking the “Enroll Now” button on our course page and completing the registration form followed by payment.

ECOSYSTEM

Why Learn AI & Machine Learning Today?

Artificial Intelligence (AI) and Machine Learning (ML) are not just buzzwords — they are the future shaping almost every industry worldwide. From self-driving cars to personalized recommendations on your favorite apps, AI and ML technologies are revolutionizing how we live, work, and solve problems.

By learning AI and ML today, you’re stepping into a world of endless opportunities:

Future-Proof Yourself: As automation accelerates, having AI expertise makes you indispensable in the job market.

Transform Ideas into Reality: Build intelligent systems that can learn, adapt, and improve themselves.

Boost Your Career Prospects: AI and ML skills are among the highest-demanded in tech, opening doors to exciting job roles and high salaries.

Solve Real-World Problems: From healthcare to finance, AI is enabling breakthroughs that make lives better and businesses smarter.

AI Summer Bootcamp 2025