★ IGNITING INNOVATORS FOR TOMORROW
Explore All 6 Workshops
The Neural Square / Workshops / AI & ML 5-Day Workshop
Official Syllabus & Program Guide

AI and ML WORKSHOP

A Hands-on 5-Day Workshop: From Python fundamentals to building and deploying real AI applications

This workshop takes participants on a structured journey from core Python programming to building and deploying real-world AI/ML applications. Each day combines focused theory with a substantial hands-on project, so learners leave with working code and a portfolio-ready capstone application.

Duration 5 Days · ~6 hours/day
Experience Level Beginner → Intermediate
Pedagogical Ratio 30–40% Theory + 60–70% Labs
Format Instructor-led + Guided Labs
Certification Official Certificate on Day 5
Target Audience Science & Engineering Students
Target Capabilities

By the End of the Workshop, Students Will Be Able To

Concrete, verifiable technical capabilities developed through guided programming labs.

Write Python Confidently

Confidently write Python programs utilizing core syntax, control flow, nested collections, functions, and structured file handling.

Clean & Analyze Datasets

Load, sanitize, manipulate, and visualize real-world messy datasets using high-performance NumPy arrays and Pandas dataframes.

Train Machine Learning Models

Formulate supervised and unsupervised problems: train Linear/Logistic Regression, Decision Trees, Random Forests, and K-Means algorithms.

Understand Neural Architecture

Understand the inner mechanics of neural networks: input/output weights, biases, non-linear activation functions, backpropagation, and loss functions.

Create and Deploy Complete ANN Models

Overcome real-world training obstacles: resolve overfitting, apply normalization techniques, tune hyperparameters, and deploy complete, functional Artificial Neural Network models for capstone demonstration.

Hour-by-Hour Timetable

5-Day Comprehensive Curriculum

Explore the exact schedule and session activities planned for each day of the workshop.

Day 1: Python Programming

AI/ML/DL intro, Python basics, data types, control flow, functions, file handling.

6 Hours Total
10:00 – 11:15

Opening Ceremony & Orientation

Welcome address, workshop objectives, setup verification, and instructor introductions.

11:15 – 1:00

Python Foundations

Core syntax, data types (Lists, Dictionaries), control flow, and assignment operators.

1:00 – 2:00

Lunch Break

2:00 – 3:00

Hands-on Lab: Logic & Functions

Hands-on lab practicing If/Else logic, for/while loops, and writing modular functions.

3:00 – 5:00

Python Problem Solving

Guided algorithmic challenge set and structured file manipulation.

Day 2: Data Science & Machine Learning Introduction

NumPy, Pandas, data cleaning, Matplotlib, Supervised vs. Unsupervised learning, regression, classification.

6 Hours Total
10:00 – 1:00

Data Analysis & Manipulation

NumPy array structures, matrix operations, Pandas DataFrames, data cleaning, and Matplotlib plotting.

1:00 – 2:00

Lunch Break

2:00 – 3:00

Introduction to Machine Learning

Supervised vs. Unsupervised learning paradigms, train/test split concepts, and model evaluation metrics.

3:00 – 5:00

ML Algorithms Coding Lab

Linear Regression and Logistic Regression derived and implemented in code.

Day 3: Machine Learning Algorithms

Decision Trees, Random Forest, K-Means Algorithm, and practical model building.

6 Hours Total
10:00 – 1:00

Advanced ML Algorithms

Decision Trees splitting criteria, Random Forest ensembles, and unsupervised K-Means clustering.

1:00 – 2:00

Lunch Break

2:00 – 3:00

Hands-on Practice: Model Building

Training and validating classification and clustering pipelines on real-world datasets.

3:00 – 5:00

Hands-on Practice: Pipeline Prototyping

Hyperparameter evaluation, cross-validation scoring, and model tuning.

Day 4: Neural Networks & Deep Learning

Introduction to neural networks, building Artificial Neural Network (ANN) models.

6 Hours Total
10:00 – 1:00

Introduction to Neural Networks

Neurons, input/output weights, biases, Activation Functions, Loss Functions, Backpropagation, and Optimizers.

1:00 – 2:00

Lunch Break

2:00 – 3:00

Model Training: Building the ANN

Defining network layers, forward passes, loss calculation, and backward weight updates.

3:00 – 5:00

Hands-on Practice: Custom ANN Model

Coding and training your own complete ANN model in Python/PyTorch.

Day 5: Final Project Building & Presentations

Overfitting control, hyperparameter tuning, project presentations, and certification.

6 Hours Total
10:00 – 12:00

Resolving Issues While Model Building

Overfitting control, normalization & numerical stability, and hyperparameter tuning.

12:00 – 1:00

Project Building Sprint: Part 1

Capstone construction and final data integration.

1:00 – 2:00

Lunch Break

2:00 – 3:00

Project Building Sprint: Part 2

Polishing models, generating evaluation curves, and preparing demonstrations.

3:00 – 4:00

Project Presentations

Student presentations defending their model architectures and results.

4:00 – 5:00

Closing Ceremony & Certificate Distribution

Graduation recognition and awarding of official certificates.

Academic Leadership

Meet the Instructors

Alumni and researchers from IIT Hyderabad and NIT Nagpur combining theoretical physics depth with hands-on coding mastery.

PR

Pushkaraj Rode

M.Sc in Physics @ IIT Hyderabad
Research Specialization

Quantum Field Theory, Quantum Chromodynamics, Renormalization, Scattering cross sections and Decay width Calculations.

📱 +91 7498681845
DT

Durgesh Thail

M.Sc in Physics @ NIT Nagpur
Research Specialization

Quantum Information Theory, Quantum Entanglement, Numerical techniques, Multibody physics, Simulations, Computational techniques for numerical solutions.

📱 +91 9373829481
Checklist

Tools & Requirements

Everything needed for full participation in the coding labs.

Software Tools

Google Colab
Python 3.x
Jupyter Notebook
VS Code & Git/GitHub

Python Libraries

NumPy & Pandas
Matplotlib
PyTorch
TensorFlow

Hardware

Personal Laptop
8 GB RAM recommended
Stable Internet Connection

Prerequisites

Beginner's experience on any programming language
Basic high-school algebra
Curiosity to build real systems