A new loss proposed that are sensitive towards image corruption and high information to noise trade off
-
Updated
Jan 23, 2023 - Jupyter Notebook
A new loss proposed that are sensitive towards image corruption and high information to noise trade off
A codebase for a traffic optimization research project.
Alternative loss function of binary cross entropy and focal loss
Toolbox of analysis for the related paper. /!\ In progress
OpenLoss: This repository discloses cost functions designed for open-set classification tasks, namely, Entropic Open-set, ObjectoSphere and Maximal-Entropy Loss.
This Repository contains material to learn about machine learning algorithms concepts along with implementation. This also provides you the material to prepare yourself for interviews.
Deep Learning Loss Functions
Design of a CNN (Convolutional Neural Networks) to classify CIFAR-10 images
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
Evolutionary search for survival analysis loss function for neural networks
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
Inverse Supervised Learning
📄 Official implementation regarding the paper "Programmatically Evolving Losses in Machine Learning".
Generating a TensorFlow model that predicts values in a sinewave
Bahdanau Attention Mechanism | Tensorflow Custom Layers/Model/Loss Function/Metrics | LSTM | Encoder | Decoder | Cross-Attention | Language Translation | Bleu Score | Dropout
An HR predictive analytics tool for forecasting the likely range of a worker’s future job performance using multiple ANNs with custom loss functions.
A neat, lightweight and single neuron perceptron written in C++ from scratch without any external library, trained using the perceptron trick and loss function
Add a description, image, and links to the loss-function topic page so that developers can more easily learn about it.
To associate your repository with the loss-function topic, visit your repo's landing page and select "manage topics."