A demonstration of how to use PyTorch to implement Support Vector Machine with L2 regularizition and multiclass hinge loss

Official project of DiverseSampling (ACMMM2022 Paper)

The goal of this project is to design a classifier to use for sentiment analysis of product reviews. Our training set consists of reviews written by Amazon customers for various food products. The reviews, originally given on a 5 point scale, have been adjusted to a +1 or -1 scale, representing a positive or negative review, respectively.

(Python, R, C) Sparse binary matrix factorization with hinge loss

Implemeting SVM to classify images with hinge loss and the softmax loss.

This Repository consists of the solutions to various tasks of this course offered by MIT on edX

Jittor reimplementation of DiverseSampling (MM22)

Verified the robustness to outliers of Huber Loss with Hinge loss for classification over different datasets.

Neural Network implemented with different Activation Functions i.e, sigmoid, relu, leaky-relu, softmax and different Optimizers i.e, Gradient Descent, AdaGrad, RMSProp, Adam. You can choose different loss functions as well i.e, cross-entropy loss, hinge-loss, mean squared error (MSE)

The Credit Card Fraud Detection Dataset can be found in Kaggle.

VerDisGAN and HorDisGAN which control the variation degrees for generated samples

These are coding assignments and projects for the CS 675 Machine Learning course.

This repository serves as a storage location for the documentation and implementation of my master thesis, including the source code, written report, and presentation.

Assignments and Project from NJIT CS 675

• Machine Learning • In this project we focused on comparing a Bayes optimal classifier with neural network models using different methods, including cross-entropy, exponential, and hinge loss functions.