Sort by:
A research toolkit for understanding how misinformation flows through a social network using dynamic system simulation and graph neural networks
A deep learning application with iOS end to learn about user room style and recommend new furniture, and visualize furniture in their room using augmented reality
An automated end-to-end pipeline for dataset discovery, collection, and model building. Classification simplified.
Anonymous posts are vital to all communities. Big Red Confession Wall allows people to freely and anonymously voice their ideas.
End-to-end music demixing with PyTorch
"Stop thinking with your head" - Making a simple, small, and fast experimental architecture based on RNNs that emulates Transformers
It's Dance Time! Get your personal dance trainer and compete to be the best dancer
PytorchCV allows users to easily annotate images using a label system for classification problems, a bounding box for localization, and a polygon tool or freehand selection for segmentation tasks.
Generate Music with AI
EmoAR is a mobile AR app that aims to recognize facial expression in real time and to superimpose virtual content according to the recognized facial expression. We also created a web app (without AR).
Preprocess selected classical music and train a GAN to attempt creation and discrimination of the GAN based on significant characteristics learned from a generated spectrogram waveform.
Automated task/test framework for differentiable software.
Helps report suicidal tendencies using NLP sentiment analysis, and connects users with help.
To help people create and automate quality social media post to bring more traffic and awareness to their brand. Beside, it also a machine to help people think about the content with image or text.
There are over 280 million blind and visually impaired people around the world who have problems that seem small to people with more abilities (such as pairing socks) but to them they are huge.
Making the world a better place one posture at a time
Detoxify is a Chrome extension which detects, classifies and highlights toxic comments in English under Youtube videos with the power of Deep Learning
Code for Hands On Intelligent Agents with OpenAI Gym book to get started and learn to build deep reinforcement learning agents using PyTorch
Everyone should be able to see. We built Vision to help anyone see, using only a smartphone. Through the use of haptic feedback, voice captions and
A Python library for recommender system. RecLib makes it easy to design and evaluate deep learning models for recommender system, along with the infrastructure to easily run them in the cloud.
Democratizing healthcare with AI to uplift underprivileged communities
Low cost solution to detect pneumothorax using raspberry pi for remote areas where there are no radiologist.
MoveOut aims to assist students looking to move out from home by providing lifestyle estimates using advanced machine learning algorithms, trained on over 10,000 customers and millions of transactions
XPlore is a tool designed for understanding, analyzing and annotating medical images like Xrays ,MRIs, CT scans. The intended audience are both data scientists and medical professionals.
