Assessfy Foundation Projects Lab Beginner 5 milestones 100 marks

Build Your Own Handwritten Number Recognizer

Discipline: AI & Machine Learning Level: Foundation Industry: AI & Data Function: Engineering Team: up to 3 Assessment: 5 milestones (100 marks)

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

What you'll build: You'll create a simple computer program that can look at pictures of handwritten digits (0-9) and guess what number they are. You'll use a basic neural network and a famous dataset called MNIST to teach your program how to recognize these numbers.

Why it's a good starter: This project is designed for beginners and uses easy-to-follow steps. You'll get hands-on experience with the fundamentals of artificial intelligence without needing any advanced math or programming skills. All the tools are free and widely used!

What you'll learn: You'll discover how images are handled in AI, how neural networks are built and trained, and how to evaluate your model's accuracy. These skills are a great foundation for more advanced projects in machine learning.

Milestones

1. Setup & Project Plan

10 marks 5d

Submit a short project plan outlining your approach. Successfully install Python and access Jupyter Notebook or Google Colab. Download the MNIST dataset. Show a screenshot of your setup and a brief plan (1-2 paragraphs).

2. Build Neural Network (Part 1)

30 marks 10d

Load the MNIST data, visualize a few sample images, and preprocess them for the neural network. Submit code and screenshots showing data loading, image display, and preprocessing steps completed.

3. Build Neural Network (Part 2) & Training

30 marks 10d

Construct a simple neural network model using Keras, then train it on the MNIST data. Submit the code for your model architecture and training process, along with graphs or logs showing the training progress.

4. Testing & Polish

20 marks 7d

Evaluate your model's accuracy on test data and present results (accuracy score, confusion matrix or sample predictions). Submit your evaluation code and a brief summary of results. Make any final improvements.

5. Demo & Short Report

10 marks 5d

Prepare a short demo (screenshots or a notebook walkthrough) and write a 1-page summary explaining what you built, how it works, and what you learned. Submit your demo materials and report.

Open internships using this project -->

Skills you'll learn

AI & Machine LearningLoading and visualizing image dataBuilding a basic neural networkTraining a model on sample dataEvaluating model performancePresenting results clearly

Tools used

PythonJupyter Notebook or Google ColabKeras (with TensorFlow backend)MNIST dataset

Prerequisites

Basic programming (e.g. Python)School-level maths (additionmultiplication)Curiosity and willingness to learn

Available mentors

No mentors have signed up for this project yet.

Be the first to mentor

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

Build Your Own Handwritten Number Recognizer

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Beginner

Build Your Own Handwritten Number Rec…

Assessfy

Auto-issued on completion One-click LinkedIn add