Code for the paper "A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses" (ECCV 2020 - Spotlight)

Easy to use class balanced cross entropy and focal loss implementation for Pytorch

Code lab for deep learning. Including rnn,seq2seq,word2vec,cross entropy,bidirectional rnn,convolution operation,pooling operation,InceptionV3,transfer learning.

A python metaheuristic optimization library. Currently supports Genetic Algorithms, Gravitational Search, Cross Entropy, and PBIL.

Implementation of Reinforcement Algorithms from scratch

compare the performance of cross entropy, focal loss, and dice loss in solving the problem of data imbalance

Numerically Stable Cross Entropy Loss Function Implemented with Python and Tensorflow

Song lyrics generation using Recurrent Neural Networks (RNNs)

We apply the noisy cross-entropy method to the game of Tetris to demonstrate its efficiency.

A data classification using MLP

A pytorch implementation of Densenet for FashionMNIST dataset

PyTorch Implementation of Robust Cross Entropy Loss (Loss Correction for Label Noise)

Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations

A library for working with 1D piecewise linear probability density functions.

Simple neural network classifier on the MNIST digit set

The Project IsoCrypto was inspired by statistical tools applied in the data mining of astrophysics data. The main references were theoretical curves adjusted in open clusters – these curves are called isochrones. Therefore, this project aims to amplify the applications of those curves in econophysics.

Investigating the Behaviour of Deep Neural Networks for Classification

A simple implementation of a transformer based language model using Pytorch-Lightning