Artificial Intelligence Learning Notes.

[ECCV2024 - Oral] Adaptive Parametric Activation

WraAct is a tool to construct the convex hull of various activation functions.

ActTensor: Activation Functions for TensorFlow. https://pypi.org/project/ActTensor-tf/ Authors: Pouya Ardehkhani, Pegah Ardehkhani

[ICLR 2024] Dynamic Neural Response Tuning

Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction

Javascript implementation of some activation functions.

Source for the paper "Universal Activation Function for machine learning"

Understanding DNN

This program implements logistic regression from scratch using the gradient descent algorithm in Python to predict whether customers will purchase a new car based on their age and salary.

[NeurIPS 2024] Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks

Neural_Networks_From_Scratch

:white_check_mark: Optimized Swish activation function, for neural networks

m-arcsinh: A Reliable and Efficient Function for Supervised Machine Learning (scikit-learn, TensorFlow, and Keras) and Feature Extraction (scikit-learn)

Implementing an Image classification neural network to classify Street House View Numbers

WraLU is an artifact for the paper "ReLU Hull Approximation" (POPL'24), which provides a sound but incomplete neural network verifier by over-approximating ReLU function hull.

Hyper-Flexible Convolutional Neural Networks Based on Generalized Lehmer and Power Means

:package: Non-official SPOCU activation function implementation for Pytorch and Tensorflow.

A small walk-through to show why ReLU is non linear!

ReLU++: A modified ReLU activation function with enhanced performance for deep learning models.

PyTorch implementation of the Leaky Hardtanh activation function

This repository offers a Python Package for the PyTorch implementation of the APTx activation function, as introduced in the paper "APTx: Better Activation Function than MISH, SWISH, and ReLU's Variants used in Deep Learning".

Logit-space logical activation functions for pytorch

Comparative Analysis of Activation Functions in Shallow Neural Networks for Multi-Class Image Classification Using MNIST Digits and CIFAR-10 Datasets with Fixed Architectural Parameters

WraAct is an artifact for the paper "Convex Hull Approximation for Activation Functions" (OOPSLA'25), which provides a sound but incomplete neural network verifiers by over-approximating the function hulls of various activation functions (including leaky ReLU, ReLU, sigmoid, tanh, and maxpool).

step by step tutorial for ANN

This repository provides a comprehensive machine learning course with theoretical concepts and practical implementations

This project demonstrates how to build and optimize a CNN for classifying images from the Fashion MNIST dataset using TensorFlow, Keras, and Keras Tuner.

implementation of Claru activation function

A feedforward multilayer perceptron with gradient descent & backpropagation written from scratch in Java