ankonzoid/NN-scratch
Coding up a Neural Network Classifier from Scratch
This project helps data science students and enthusiasts understand the core mechanics of neural networks. It takes a dataset like the 'seeds' dataset (numerical features describing different seed varieties) and demonstrates how a simple neural network can classify them into their respective types. The output shows the accuracy of the model, allowing learners to see how a network trains and performs without relying on high-level libraries.
No commits in the last 6 months.
Use this if you are a student or beginner in machine learning who wants to learn how a basic neural network works by seeing it coded from fundamental mathematical operations.
Not ideal if you need a robust, production-ready neural network solution or are looking for advanced deep learning architectures and features.
Stars
81
Forks
27
Language
Python
License
MIT
Category
Last pushed
Feb 03, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ankonzoid/NN-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.