As a graduate or PhD student, this academic program assists you in furthering your research. It provides opportunities for you to share your expertise and experience with other students, data scientists, and developers in the community.
This project showcases the use of automatic differentiation and the Adam optimization technique to update a target image according to content and style images, and exposes the style transfer model via a REST API.
This idea describes an approach to detect mental stress using unobtrusive wearable sensors. The approach relies on estimating the state of the autonomic nervous system from an analysis of heart rate variability. It uses a nonlinear system identification technique known as principal dynamic modes (PDM) to predict the activation level of the two autonomic branches: sympathetic (that is, stress inducing) and parasympathetic (that is, relaxation related).
This project is a virtual outfit decider system that allows users to fit clothing and hairstyles using machine perception. From an input image, the user draws a rectangle around the extraction region for clothing and hair.
HadaNets introduces a flexible train-from-scratch tensor quantization scheme by pairing a full precision tensor to a binary tensor in the form of a Hadamard product. Unlike wider reduced precision neural network models, train-time parameter count is preserved, thus outperforming XNOR-Nets without a train-time memory penalty.
This is a unified framework that integrates various components of a fact-checking process: document retrieval from media sources with various types of reliability, stance detection of documents with respect to given claims, evidence extraction, and linguistic analysis. FAKTA predicts the factuality of given claims and provides evidence at the document and sentence level to explain its predictions.
Learn about this new deep learning method for the automatic delineation and segmentation of brain tumors from multisequence magnetic resonance imaging (MRI). A Radiomics* model for predicting the overall survival is designed based on the features extracted from the segmented volume of interest.