t9nzin/mnist-from-scratch
a feedforward neural network from scratch
This project helps machine learning practitioners learn the foundational mechanics of neural networks. It takes raw numerical data representing handwritten digits and outputs a trained model that can classify new handwritten digits. This is ideal for those who want to understand the inner workings of a neural network classifier.
No commits in the last 6 months.
Use this if you are a machine learning student or enthusiast who wants to learn how a basic neural network is built from the ground up, without relying on high-level libraries for the core algorithms.
Not ideal if you need a production-ready solution for digit classification or a highly optimized and scalable deep learning framework.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Aug 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/t9nzin/mnist-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.