NDLI: MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints

Please wait, while we are loading the content...

LiveLabs: Building In-Situ Mobile Sensing & Behavioural Experimentation TestBeds

Listening through a Vibration Motor

Beetle: Flexible Communication for Bluetooth Low Energy

Mobility Modeling and Prediction in Bike-Sharing Systems

DefDroid: Towards a More Defensive Mobile OS Against Disruptive App Behavior

Expansion of Human-Phone Interface By Sensing Structure-Borne Sound Propagation

FOCUS: Robust Visual Codes for Everyone

CASE: Comprehensive Application Security Enforcement on COTS Mobile Devices

Platypus: Indoor Localization and Identification through Sensing of Electric Potential Changes in Human Bodies

Practical Human Sensing in the Light

MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints

Defending against Sybil Devices in Crowdsourced Mapping Services

I-Pic: A Platform for Privacy-Compliant Image Capture

FlashBack: Immersive Virtual Reality on Mobile Devices via Rendering Memoization

Practical Bluetooth Traffic Sniffing: Systems and Privacy Implications

Targeted Mimicry Attacks on Touch Input Based Implicit Authentication Schemes

The Design and Implementation of a Mobile RFID Tag Sorting Robot

I am a Smartwatch and I can Track my User's Arm

TaskFolder: Dynamic and Fine-Grained Workload Consolidation for Mobile Devices

TransitLabel: A Crowd-Sensing System for Automatic Labeling of Transit Stations Semantics

What You Mark is What Apps See

uLink: Enabling User-Defined Deep Linking to App Content

Characterizing and Improving WiFi Latency in Large-Scale Operational Networks

Privacy Capsules: Preventing Information Leaks by Mobile Apps

Idea: A System for Efficient Failure Management in Smart IoT Environments

BodyScan: Enabling Radio-based Sensing on Wearable Devices for Contactless Activity and Vital Sign Monitoring

Understanding the Characteristics of Android Wear OS

Reactive Control of Autonomous Drones

Viola: Trustworthy Sensor Notifications for Enhanced Privacy on Mobile Systems

ReCon: Revealing and Controlling PII Leaks in Mobile Network Traffic

Regulating ARM TrustZone Devices in Restricted Spaces

MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints

Content Provider	ACM Digital Library
Author	Han, Seungyeop Shen, Haichen Krishnamurthy, Arvind Philipose, Matthai Wolman, Alec Agarwal, Sharad
Abstract	We consider applying computer vision to video on cloud-backed mobile devices using Deep Neural Networks (DNNs). The computational demands of DNNs are high enough that, without careful resource management, such applications strain device battery, wireless data, and cloud cost budgets. We pose the corresponding resource management problem, which we call Approximate Model Scheduling, as one of serving a stream of heterogeneous (i.e., solving multiple classification problems) requests under resource constraints. We present the design and implementation of an optimizing compiler and runtime scheduler to address this problem. Going beyond traditional resource allocators, we allow each request to be served approximately, by systematically trading off DNN classification accuracy for resource use, and remotely, by reasoning about on-device/cloud execution trade-offs. To inform the resource allocator, we characterize how several common DNNs, when subjected to state-of-the art optimizations, trade off accuracy for resource use such as memory, computation, and energy. The heterogeneous streaming setting is a novel one for DNN execution, and we introduce two new and powerful DNN optimizations that exploit it. Using the challenging continuous mobile vision domain as a case study, we show that our techniques yield significant reductions in resource usage and perform effectively over a broad range of operating conditions.
Starting Page	123
Ending Page	136
Page Count	14
File Format	PDF EPUB
ISBN	9781450342698
DOI	10.1145/2906388.2906396
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-06-20
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Approximation Dnn Video Recognition
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

MCDNN: An Execution Framework for Deep Neural Networks on Resource-Constrained Devices

Combining information from multi-stream features using deep neural network in speech recognition

Execution interval analysis under resource constraints

Maximizing Determinism in Stream Processing Under Latency Constraints

Modular Parallelization Framework for Multi-Stream Video Processing

Smart Care Using a DNN-Based Approach for Activities of Daily Living (ADL) Recognition

An Investigation of Deep Learning Models for EEG-Based Emotion Recognition

STYX: Stream Processing with Trustworthy Cloud-based Execution

Two-stage ASGD framework for parallel training of DNN acoustic models using Ethernet

MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints

Similar Documents

MCDNN: An Execution Framework for Deep Neural Networks on Resource-Constrained Devices

Combining information from multi-stream features using deep neural network in speech recognition

Execution interval analysis under resource constraints

Maximizing Determinism in Stream Processing Under Latency Constraints

Modular Parallelization Framework for Multi-Stream Video Processing

Smart Care Using a DNN-Based Approach for Activities of Daily Living (ADL) Recognition

An Investigation of Deep Learning Models for EEG-Based Emotion Recognition

STYX: Stream Processing with Trustworthy Cloud-based Execution

Two-stage ASGD framework for parallel training of DNN acoustic models using Ethernet

MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints