Projects
Our objective is to develop a library of efficient machine learning algorithms that can run on severely resource-constrained edge and endpoint IoT devices ranging from the Arduino to the Raspberry Pi.
Established:
VideoKheti is a multimodal video search system for low-literate farmers that combines local language speech, graphics and touch interaction to help find and watch agriculture extension videos (of digitalGreen), in the farmer’s own language and dialect.
In the Harnessing AutoMobiles for Safety (HAMS) project, we use low-cost sensing devices to construct a virtual harness for vehicles. The goal is to monitor the state of the driver and how the vehicle is being driven in the context…
Established:
The CoCoNet project arises from the quest to have the best of both worlds, specifically, having the operational benefits of centralization along with the performance benefits of distribution.
Established:
NEWS: The ACM SenSys 2008 paper on Nericell received both the ACM SIGMOBILE Test-of-Time Award and the ACM SenSys Test-of-Time Award in 2019. The Nericell project focuses on road and traffic monitoring using an ensemble of mobile smartphones carried by people…
Scaling performance beyond Moore’s law Domain specialization is expected to play a big role in how computer systems evolve in future. With the end of Moore’s law, we are already seeing CPU, GPU and domain specific hardware evolving rapidly. The next decade is therefore expected to see big changes in how we develop, compile and run software. This project focuses on data systems, a class of systems where, as the data sizes grow, performance scaling is going to be of importance.First, we believe that domain-specific compilers will play a crucial strategic role in helping software leverage the changing hardware landscape. Such compilers will…
Holistic optimization of large-scale networked services The growth of large-scale networked services has brought to the fore myriad challenges: performance, reliability, efficiency, cost, and more. Traditionally, work on addressing and balancing these has been done in silos. For instance, an…
Established:
We are re-thinking how systems can be designed to empower Artificial Intelligence (AI)/deep learning researchers, developers and users. Deep Learning Model Training One example is the Gandiva cluster scheduler project. Deep learning training jobs are compute-hungry. Thus, they are typically…
Established:
One of the biggest healthcare problems facing the world today is mental illness. In the “moments of change” project, we are exploring how technology can play a role in connecting people in need to mental health professionals.