Research

Our goal is to build an AI-powered personal digital nutritionist that enables users to track the food they eat simply by speaking or typing natural English phrases.

We develop a computational model that explains how people make causal judgments in physical scenes by mentally simulating counterfactual outcomes and comparing those to what actually happened.

Our goal is to build a system that predicts where people are looking in images. Given an image and the location of a head, our approach follows the gaze of the person and identifies the object being looked at.

Solid aims to radically change the way Web applications work today, resulting in true data ownership as well as improved privacy.

We develop algorithms for fetal MRI interpretation, to enable noninvasive fetal monitoring from MRI.

Our goal is to develop algorithms for allowing robots to adapt intelligently to humans when they are working together as a team.

Uhura is an autonomous system that collaborates with humans in planning and executing complex tasks, especially under over-subscribed and risky situations.

We aim to develop a context-aware data-driven functional genomics framework that can characterize tissue-specific gene representations, provide context-aware genotype to phenotype mapping, and enable network-based exploration of disease genetics.

We develop algorithms, systems and software architectures for automating reconstruction of accurate representations of neural tissue structures, such as nanometer-scale neurons' morphology and synaptic connections in the mammalian cortex.

We aim to study the causes and transmission modes of infectious diseases among members of a community in the presence of hidden, asymptomatic spreaders of the pathogen.

Transitioning machine learning models across electronic health record (EHR) versions can be improved by mapping different EHR encodings to a common vocabulary.

Our goal is to develop better metagenomic binning by origin species of fragments of sequenced environmental DNA.

We develop, parameterize, and validate a model for tumor growth inhibition using in vivo mouse data and study the effects of modeling uncertainty and inter-individual variability on drug candidate efficacy predictions.

This project uses computational biology and chemistry tools to design a pharmaceutical to combat the Zika Virus.

We use computational models of biological pathways in disease to estimate the range of possible responses to various hypothetical drugs, given patient variability and limited pathway-relevant data.

We enable independent navigation for visually impaired users through a wearable feedback system using time-of-light sensors or depth cameras.

Models and algorithms to predict in real time the next actions of a human working together with a robot

The goal of this project is to develop and test a wearable ultrasonic echolocation aid for people who are blind and visually impaired. We combine concepts from engineering, acoustic physics, and neuroscience to make echolocation accessible as a research tool and mobility aid.

A polyhedral compiler for expressing image processing, DNN, and linear/tensor algebra applications

Our team uses accelerometers and machine learning to help detect vocal disorders. We capture data about the motions of patient's vocal folds to determine if their vocal behavior is normal or abnormal.

Our focus is using computational tools to summarize health-related data to help clinicians focus on decision-making rather than just keeping up with the data.

Our focus is on improving health-related outcomes by creating machine learning models that improve human risks.

Existing methods for cloning and recombination of DNA enable construction of arbitrary sequences. However, the sequential nature of these techniques makes them time-consuming and expensive. Furthermore, while the transformation of an existing plasmid into a host strain can be reliable when a selection marker is used, there are many current limitations: the number of different plasmids that can be co-transformed is limited by the choice of markers and compatible origins of replication; plasmids are less stable than chromosomal DNA and are difficult to maintain indefinitely without mutation; and cistronic interactions cannot be designed since each new nucleotide sequence added is on an unconnected DNA molecule. To overcome these limitations, we are designing reconfigurable chromosomes consisting of both fixed and variable regions. While the fixed region is carefully optimized and tuned ahead of time, the variable region can be modified in the field, at the point-of-use, leading to rapid and on-demand realization of novel biocircuits with many different phenotypes.

In order to be able to design synthetic organs that function autonomously, we will need to engineer artificial tissue homeostasis. To control the size of these artificial tissues, two major mechanisms will have to be engineered.