samas69420/basedNN
neural networks without libraries
This is a collection of neural network implementations built using only raw Python. It allows computer science students or aspiring machine learning engineers to understand the fundamental algorithms of neural networks, like backpropagation, by examining simple and highly readable code. You input network parameters and data, and it outputs the trained model, offering a transparent view into how these systems work without abstracting away details with complex libraries.
No commits in the last 6 months.
Use this if you are a student or educator looking to understand the foundational math and algorithms of neural networks, such as backpropagation, through clear and simple Python code.
Not ideal if you need to train models for real-world applications or require efficient processing of large datasets, as it lacks optimizations like vectorization or GPU support.
Stars
12
Forks
—
Language
Python
License
—
Category
Last pushed
Jun 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/samas69420/basedNN"
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.