The purpose of this research project is to compare traditional CNNs to vision transformers, can transformers give a higher AUC when classifying Atypical Femoral Fracture / Normal Femoral Fracture?

Common approaches to text augmentation, from random text-editing perturbations, back translation, to model-based transformations.

This repository contains code and resources for building a Convolutional Neural Network (CNN) that can recognize American Sign Language (ASL) images. The model is capable of classifying letters in ASL using high accuracy. The process involves data preprocessing, creating a CNN model, training, evaluation, and utilizing the trained model to recogniz

A study that aims to unfold what emotions did Filipino students manifest during a year of Covid-19 quarantines.

This is an effort to provide different approaches towards human action recognition from video. A method to perform data augmentation on skeletal data so as to achieve a view independent recognition approach is included.

[KDD23] Official PyTorch implementation for "Improving Conversational Recommendation Systems via Counterfactual Data Simulation".

Augmentation for CV using frequency shortcuts

Extra bits of unsanitized code for plotting, training, etc. related to our CVPR 2021 paper "Augmentation Strategies for Learning with Noisy Labels".

This project investigates the impact of generative AI on the performance of convolutional neural networks (CNNs) in image classification tasks, specifically in the context of limited data.

Unleashing the Power of CNNs for Precise American Sign Language Recognition.

Spotify Classification Problem 2023

Disease - Symptom Dataset Cleaning and Augmenting Process

My demonstration of RNN, LSTM, Dropouts, and Data Augmentation Techniques for Texts using Spam and Ham Dataset.

Computational toolkit for efficient prediction of the thickness of 2D materials

Implementation of our paper "Learning to Substitute Span towards Improving Compositional Generalization" @ ACL'2023, Toronto, Canada.

A light weight CLI for augmenting image datasets for deep learning and ML projects

A toolkit to augment audios (e.g. noise, reverb, distort, speedup, packet loss, farfield effects).

Neural Fuzzy Repair (NFR) is a data augmentation pipeline, which integrates fuzzy matches (i.e. similar translations) into neural machine translation.

Codes for employing PySimMIBCI for MI-EEG data generation and for using such data with FBCNetToolbox models