ScottT2-spec/mnist-neural-network-
Neural network from scratch (NumPy only, 96% accuracy) + Kaggle Digit Recognizer competition entry (99.685% accuracy, top 40). No frameworks for the from-scratch version.
This project offers two ways to build or understand systems that recognize handwritten digits. It takes images of individual digits (0-9) as input and outputs which digit is present in the image. This is ideal for data scientists, machine learning engineers, or students learning about neural networks and image classification.
Use this if you need to accurately identify handwritten digits from images or if you want to learn the fundamental mechanics of neural networks from the ground up.
Not ideal if you need to classify complex images with many objects or if you require an extremely fast training time for a production system.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ScottT2-spec/mnist-neural-network-"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
greydanus/mnist1d
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep...
potterhsu/SVHNClassifier
A TensorFlow implementation of Multi-digit Number Recognition from Street View Imagery using...
potterhsu/SVHNClassifier-PyTorch
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep...
kensanata/numbers
Handwritten digits, a bit like the MNIST dataset.
kdexd/digit-classifier
A single handwritten digit classifier, using the MNIST dataset. Pure Numpy.