May 10, 2023
An implementation of the ViT model from "An Image is Worth 16X16 Words: Transformers for Image Recognition at Scale" by Dosovitskiy et al. (to be updated)
May 9, 2023
AI model explainability, introducing a detailed rubric for evaluating and improving the transparency of AI models (to be updated)
September 14, 2019
A mobile app and a deep learning model, LytNetV2, to assist the visually impaired in crossing intersections through real-time auditory and vibration feedback. (to be updated)
July 23, 2019
A novel CNN architecture, LYTNet, to provide the visually impaired with real-time information on traffic light status and crosswalk direction.