itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
Implements diverse neural network algorithms beyond standard deep learning, including Self-Organizing Maps (SOM), Growing Neural Gas, and unsupervised learning methods for topology discovery and data visualization. Provides high-level abstractions for backpropagation variants, hyperparameter optimization strategies, and pre-trained model integration, making it well-suited for educational exploration and algorithm comparison rather than production deployment.
734 stars. No commits in the last 6 months.
Stars
734
Forks
160
Language
Python
License
MIT
Category
Last pushed
Nov 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/itdxer/neupy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.
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.
marcpinet/neuralnetlib
🧠A flexible machine & deep learning framework built from scratch using only NumPy