62 citations · 142 across the 18 of their papers we have counts for
19 papers
PIM: Video Coding using Perceptual Importance Maps
Evgenya Pergament, Pulkit Tandon, Oren Rippel +6
Human perception is at the core of lossy video compression, with numerous approaches developed for perceptual quality assessment and improvement over the past two decades. In the d…
Machine Learning Sensors
Pete Warden, Matthew Stewart, Brian Plancher +6
Machine learning sensors represent a paradigm shift for the future of embedded machine learning applications. Current instantiations of embedded machine learning (ML) suffer from c…
An Interactive Annotation Tool for Perceptual Video Compression
Evgenya Pergament, Pulkit Tandon, Kedar Tatwawadi +6
Human perception is at the core of lossy video compression and yet, it is challenging to collect data that is sufficiently dense to drive compression. In perceptual quality assessm…
Personalized Federated Learning of Driver Prediction Models for Autonomous Driving
Manabu Nakanoya, Junha Im, Hang Qiu +3
Autonomous vehicles (AVs) must interact with a diverse set of human drivers in heterogeneous geographic areas. Ideally, fleets of AVs should share trajectory data to continually re…
ML-EXray: Visibility into ML Deployment on the Edge
Hang Qiu, Ioanna Vavelidou, Jian Li +5
Benefiting from expanding cloud infrastructure, deep neural networks (DNNs) today have increasingly high performance when trained in the cloud. Researchers spend months of effort c…
Data Sharing and Compression for Cooperative Networked Control
Jiangnan Cheng, Marco Pavone, Sachin Katti +2
Sharing forecasts of network timeseries data, such as cellular or electricity load patterns, can improve independent control applications ranging from traffic scheduling to power g…
Sampling Training Data for Continual Learning Between Robots and the Cloud
Sandeep Chinchali, Evgenya Pergament, Manabu Nakanoya +5
Today's robotic fleets are increasingly measuring high-volume video and LIDAR sensory streams, which can be mined for valuable training data, such as rare scenes of road constructi…
Task-relevant Representation Learning for Networked Robotic Perception
Manabu Nakanoya, Sandeep Chinchali, Alexandros Anemogiannis +3
Today, even the most compute-and-power constrained robots can measure complex, high data-rate video and LIDAR sensory streams. Often, such robots, ranging from low-power drones to…
Characterizing and Taming Model Instability Across Edge Devices
Eyal Cidon, Evgenya Pergament, Zain Asgar +2
The same machine learning model running on different edge devices may produce highly-divergent outputs on a nearly-identical input. Possible reasons for the divergence include diff…
Multi-agent Reinforcement Learning for Networked System Control
Tianshu Chu, Sandeep Chinchali, Sachin Katti
This paper considers multi-agent reinforcement learning (MARL) in networked system control. Specifically, each agent learns a decentralized control policy based on local observatio…
RF Soil Moisture Sensing via Radar Backscatter Tags
Colleen Josephson, Bradley Barnhart, Sachin Katti +2
We present a sensing system that determines soil moisture via RF using backscatter tags paired with a commodity ultra-wideband RF transceiver. Despite decades of research confirmin…
Network Offloading Policies for Cloud Robotics: a Learning-based Approach
Sandeep Chinchali, Apoorva Sharma, James Harrison +6
Today's robotic systems are increasingly turning to computationally expensive models such as deep neural networks (DNNs) for tasks like localization, perception, planning, and obje…
Light-Field for RF
Manikanta Kotaru, Guy Satat, Ramesh Raskar +1
Most computer vision systems and computational photography systems are visible light based which is a small fraction of the electromagnetic (EM) spectrum. In recent years radio fre…
Trevor: Automatic configuration and scaling of stream processing pipelines
Manu Bansal, Eyal Cidon, Arjun Balasingam +3
Operating a distributed data stream processing workload efficiently at scale is hard. The operator of the workload must parallelize and lay out tasks of the workload with resources…
Bandana: Using Non-volatile Memory for Storing Deep Learning Models
Assaf Eisenman, Maxim Naumov, Darryl Gardner +5
Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the require…
Position Tracking for Virtual Reality Using Commodity WiFi
Manikanta Kotaru, Sachin Katti
Today, experiencing virtual reality (VR) is a cumbersome experience which either requires dedicated infrastructure like infrared cameras to track the headset and hand-motion contro…
Flashield: a Key-value Cache that Minimizes Writes to Flash
Assaf Eisenman, Asaf Cidon, Evgenya Pergament +4
As its price per bit drops, SSD is increasingly becoming the default storage medium for cloud application databases. However, it has not become the preferred storage medium for key…
Programmable Packet Scheduling
Anirudh Sivaraman, Suvinay Subramanian, Anurag Agrawal +7
Switches today provide a small set of scheduling algorithms. While we can tweak scheduling parameters, we cannot modify algorithmic logic, or add a completely new algorithm, after…
A low-latency control plane for dense cellular networks
Rakesh Misra, Sachin Katti
In order to keep up with the increasing demands for capacity, cellular networks are becoming increasingly dense and heterogeneous. Dense deployments are expected to provide a linea…