There are 2 repositories under loss-function topic.
Deep Metric Learning
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)
PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA
Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.
A dependency free library of standardized optimization test functions written in pure Python.
A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.
Angular triplet center loss implementation in Pytorch.
Tensorflow Implementation of Focal Frequency Loss for Image Reconstruction and Synthesis [ICCV 2021]
A simple 3-layer fully connected network performing the density ratio estimation using the loss for log-likelihood ratio estimation (LLLR).
Adversarial Focal Loss: Asking Your Discriminator for Hard Examples.
Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation
A neat, lightweight and single neuron perceptron written in C++ from scratch without any external library, trained using the perceptron trick and loss function
An HR predictive analytics tool for forecasting the likely range of a worker’s future job performance using multiple ANNs with custom loss functions.
Generating a TensorFlow model that predicts values in a sinewave
📄 Official implementation regarding the paper "Programmatically Evolving Losses in Machine Learning".
Inverse Supervised Learning
Bahdanau Attention Mechanism | Tensorflow Custom Layers/Model/Loss Function/Metrics | LSTM | Encoder | Decoder | Cross-Attention | Language Translation | Bleu Score | Dropout
A codebase for a traffic optimization research project.
Toolbox of analysis for the related paper. /!\ In progress
Alternative loss function of binary cross entropy and focal loss
Design of a CNN (Convolutional Neural Networks) to classify CIFAR-10 images
A new loss proposed that are sensitive towards image corruption and high information to noise trade off
Core components of neural networks An introduction to Keras Setting up a deep-learning workstation Using neural networks to solve basic classification and regression problems
Stock Trend Prediction App: In these project I created stock trend web application to predicted continuous real time trend of desired stock input taken from user with fetching data from "Yahoo Finance".
performing linear regression