mytechnotalent/HNN
A step-by-step walkthrough of the inner workings of a simple neural network. The goal is to demystify the calculations behind neural networks by breaking them down into understandable components, including forward propagation, backpropagation, gradient calculations, and parameter updates.
This project provides a detailed, step-by-step walkthrough of how a basic neural network learns. It takes simple numerical inputs and initial guesses for internal parameters, then shows you how the network processes data to produce an output, calculates errors, and adjusts its internal settings to improve accuracy. This is designed for anyone curious about the core mechanics of AI, such as students or hobbyists.
Use this if you want to understand the fundamental calculations behind neural networks, including how they make predictions and learn from mistakes.
Not ideal if you're looking for a tool to build or train complex neural networks for practical applications.
Stars
29
Forks
1
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Nov 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mytechnotalent/HNN"
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.