howion/activation-functions
Javascript implementation of some activation functions.
This JavaScript library helps machine learning developers implement various activation functions within their neural network models. It takes numerical inputs (often from a neural network layer) and applies a chosen mathematical transformation, outputting processed numbers. Developers building AI models or exploring different network architectures would use this.
No commits in the last 6 months. Available on npm.
Use this if you are a JavaScript developer building neural networks and need a collection of common activation functions readily available.
Not ideal if you are working in a language other than JavaScript or if your machine learning framework already provides these functions.
Stars
13
Forks
—
Language
JavaScript
License
MIT
Category
Last pushed
Nov 30, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/howion/activation-functions"
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.