https://github.com/xyproto/af

:zap: Activation functions for neural networks
https://github.com/xyproto/af

activation-functions neural-network nn

Last synced: 2 months ago
JSON representation

:zap: Activation functions for neural networks

• Host: GitHub
• URL: https://github.com/xyproto/af
• Owner: xyproto
• License: mit
• Created: 2017-06-10T11:16:03.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2019-10-18T21:44:15.000Z (about 5 years ago)
• Last Synced: 2024-10-05T15:20:09.850Z (3 months ago)
• Topics: activation-functions, neural-network, nn
• Language: Go
• Homepage:
• Size: 29.3 KB
• Stars: 2
• Watchers: 3
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# af [![Build Status](https://travis-ci.org/xyproto/af.svg?branch=master)](https://travis-ci.org/xyproto/af) [![Go Report Card](https://goreportcard.com/badge/github.com/xyproto/af)](https://goreportcard.com/report/github.com/xyproto/af) [![GoDoc](https://godoc.org/github.com/xyproto/af?status.svg)](https://godoc.org/github.com/xyproto/af)

Activation functions for neural networks.

These activation functions are included:

* Swish (`x / (1 + exp(-x))`)

* Sigmoid (`1 / (1 + exp(-x))`)

* SoftPlus (`log(1 + exp(x))`)

* Gaussian01 (`exp(-(x * x) / 2.0)`)

* Sin (`math.Sin(math.Pi * x)`)

* Cos (`math.Cos(math.Pi * x)`)

* Linear (`x`)

* Inv (`-x`)

* ReLU (`x >= 0 ? x : 0`)

* Squared (`x * x`)

These `math` functions are included just for convenience:

* Abs (`math.Abs`)

* Tanh (`math.Tanh`)

One functions that takes two arguments is also included:

* PReLU (`x >= 0 ? x : x * a`)

## Requirements

* Go 1.11 or later.

## General information

* License: MIT

* Version: 0.3.2

* Author: Alexander F. Rødseth <[email protected]>