Pinned Repositories
COVID-19-Scanner
This model is meant to help triage patients (prioritize certain patients for testing, quarantine, and medical attention) that require diagnosis for COVID-19. This model is not meant to diagnose COVID-19.
DataInf
deepfake_detection
fast_adversarial
[ICLR 2020] A repository for extremely fast adversarial training using FGSM
mPerturb
Implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation (Fong, et. al., 2018)
Pneumothorax
Image classifier to detect Pneumothorax (collapsed lung) on x-ray scans. It is trained on a Resnet 50 CNN model.
pytorch_influence_functions
This is a [Stable] PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
Shapley_Valuation
PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuation of Data" by Amirata Ghorbani and James Zou [ICML 2019]
spongebobNLP
GPT-2 Transformer model (with 117 million parameters) running fine-tuned for Spongebob -sounding script generation. Server-side is hosted via Google Cloud Run. Credits to minimax for making this fun API!
twitter-bias-challenge
This is a repo for analyzing Twitter's Image Crop Analysis paper (Yee, Tantipongpipat, and Mishra, 2021) for the 2021 Twitter Algorithmic Bias Challenge.
ajsanjoaquin's Repositories
ajsanjoaquin/COVID-19-Scanner
This model is meant to help triage patients (prioritize certain patients for testing, quarantine, and medical attention) that require diagnosis for COVID-19. This model is not meant to diagnose COVID-19.
ajsanjoaquin/Shapley_Valuation
PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuation of Data" by Amirata Ghorbani and James Zou [ICML 2019]
ajsanjoaquin/mPerturb
Implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation (Fong, et. al., 2018)
ajsanjoaquin/Pneumothorax
Image classifier to detect Pneumothorax (collapsed lung) on x-ray scans. It is trained on a Resnet 50 CNN model.
ajsanjoaquin/fast_adversarial
[ICLR 2020] A repository for extremely fast adversarial training using FGSM
ajsanjoaquin/DataInf
ajsanjoaquin/deepfake_detection
ajsanjoaquin/pytorch_influence_functions
This is a [Stable] PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
ajsanjoaquin/twitter-bias-challenge
This is a repo for analyzing Twitter's Image Crop Analysis paper (Yee, Tantipongpipat, and Mishra, 2021) for the 2021 Twitter Algorithmic Bias Challenge.
ajsanjoaquin/ajsanjoaquin
ajsanjoaquin/delta_def
While finetuning or prompting with correct information may alleviate biased or incorrect information, we ask how effective this approach is as we vary a Transformer model's size. We ask the question: How "fast" can the model discriminate the new and correct information from the old, harmful information?
ajsanjoaquin/spongebobNLP
GPT-2 Transformer model (with 117 million parameters) running fine-tuned for Spongebob -sounding script generation. Server-side is hosted via Google Cloud Run. Credits to minimax for making this fun API!
ajsanjoaquin/ajsanjoaquin.github.io
My personal website.
ajsanjoaquin/algos
My implementation of basic algorithms in Java for class. Primarily used for reference now.
ajsanjoaquin/chatbot_starter
Followed from a Pytorch Tutorial on making a simple chatbot
ajsanjoaquin/colorizer_GAN
Colorize Images with a Generative Adversarial Network (GAN)
ajsanjoaquin/deep-learning-v2-pytorch
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
ajsanjoaquin/Githubexplorer
Explore a selection of github repositories using a search engine with filters. Originally made to practice React.
ajsanjoaquin/GitHubGraduation-2022
Join the GitHub Graduation Yearbook and "walk the stage" on June 11.
ajsanjoaquin/introcs
My reference for Ocaml code
ajsanjoaquin/jesus-russell-obi_wan_kenobi
This is an image classifier trained on a Resnet 34 CNN model to classify images of Jesus of Nazareth (religious figure), Obi-Wan Kenobi (Jedi Master), and Russell Brand (British actor).
ajsanjoaquin/machine-learning
Content for Udacity's Machine Learning curriculum
ajsanjoaquin/meta-aria
Code for Project Aria
ajsanjoaquin/ntara
I used and created some of these functions to modify the metabolic model for Neuontobotrys tarapacana (Ntara). These files reflect the modified code started by Wayne Toh used for the same project.
ajsanjoaquin/privacy
Library for training machine learning models with privacy for training data
ajsanjoaquin/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ajsanjoaquin/pytorch-deepdream
PyTorch implementation of DeepDream algorithm (Mordvintsev et al.). Additionally I've included playground.py to help you better understand basic concepts behind the algo.
ajsanjoaquin/pytorch-YOLOv4
PyTorch ,ONNX and TensorRT implementation of YOLOv4
ajsanjoaquin/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ajsanjoaquin/yolos