-
Updated
Jun 23, 2020 - Python
#
softsign
Here are 4 public repositories matching this topic...
We introduce two novel hybrid activation functions: S3 (Sigmoid-Softsign) and its improved version S4 (Smoothed S3)
python science machine-learning research deep-learning neural-networks sigmoid softsign activation-function-exploration
-
Updated
Aug 13, 2025 - Python
Lightweight neural network library written in ANSI-C supporting prediction and backpropagation for Convolutional- and Fully Connected neural networks
neural-network image-classification convolutional-neural-network backpropagation adagrad fully-connected-network sigmoid tanh leaky-relu adam-optimizer categorical-cross-entropy softmax-layer relu-layer sgd-optimizer mean-square-error momentum-optimization-algorithm softsign glorot-uniform rmsprop-optimizer
-
Updated
Feb 24, 2025 - C
Python implementation of a simple MLP without using external packages
neural-network multi-layer-perceptron mlp-networks activation-functions backpropagation-neural-network feedforward-neural-networks softsign
-
Updated
Apr 24, 2021 - Python
Improve this page
Add a description, image, and links to the softsign topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the softsign topic, visit your repo's landing page and select "manage topics."