This is the official implementation of our ICML 2024 paper "MultiMax: Sparse and Multi-Modal Attention Learning""

This repository features hands-on Jupyter Notebooks, covering everything from fundamental concepts to advanced neural network architectures.

Open ideas. Code less. Publish more.

Interactive deep learning project to predict IPL innings scores from match context such as teams, venue, batsman, bowler, runs, wickets, and overs.

We introduce two novel hybrid activation functions: S3 (Sigmoid-Softsign) and its improved version S4 (Smoothed S3)

An Artificial Neural Network (ANN) built using PyTorch to classify images in the Fashion MNIST dataset, utilizing GPU support for improved training performance.

This is a custom-built neural network that detects handwritten numbers from image inputs. It uses ReLU activation in the hidden layers and a softmax activation function in the output layer for classification. The model is trained using backpropagation with a loss function to minimize prediction errors, achieving over 99% accuracy when predicting

This is a Fake and AI image prediction using Transfer Learning

Linear and Non Linear Activation Functions : Linear, ReLU, Sigmoid, Softmax, Tanh

A Benchmark for Activation Function Exploration for Neural Architecture Search (NAS)

Vanishing Gradient and Activation Functions

Graph by matplotlib

Neuro Flap is a Neural Network applied to the game Flappy Bird, optimised using a Genetic Algorithm. It was studied different activation functions and the impact of the number of neurons in the hidden layer on performance. Developed in C using Raylib on a Linux environment.

ZiLU Activation Function for neural networks