Overview Background Intelligence at the Edge Samsung Research Learning at the Edge: Challenges and Brainstorming Amazon Alexa Smart Home!
Background Ph.D. at UW CSE RFID, Mobile, Sensors, Data Nokia Research Samsung Research Silicon Valley Context Framework On-Device Analytics AlgoSnap Machine Learning at Amazon Alexa Smart Home
Intelligence at the Edge Edge End-points that generate data Social, Financial, Physical Sensors, Environmental Sensors, Health Sensors, Car, Home, Television, Media Consumption, Searches, Location, Calendars, Purchases
All Data All Intelligence Shared back to devices All Data...
All Data All Intelligence Shared back to devices All Data Why Not? Energy, latency, privacy...
IoT Increased Volume, Variety, Velocity! Radio Energy Smartphone Data Type Sensor Types Estimated Avg Location GPS, WiFi, Cell Towers, Bluetooth 40K / min Device Motion Accelerometer, Gyroscope, Compass 160K / min Network Latency Environmental Device Interaction Camera, microphone, Light, proximity, temperature, pressure, magnetic field keys pressed, touch screen, App usage, media usage, screen on/off, etc 37MB / min no video: (960K / min) 20K / min Privacy Social Calls, SMS, emails, Facebook, Twitter, Calendar, contacts 1K / min Interest/content Browser, search, purchases, bookmarks 20K / min Wearables Sensor + interaction data from wearables 160K-180K / min Purchases Web transactions, NFC transactions 1K / min 1.5 to 40 MB/min per user ~1 Exabyte/day at Facebook Scale
Intelligence at the Edge Save Energy: Push computation to the data Reduce Latency: Run models on the user s device Enhance Privacy: Don t upload data
Example: Centaurus - Edge Framework 1 2 3... N N+1 N+2... Concept: shift data and processing to the device-side
Example: Centaurus - Edge Framework Only High-Level Context is Sent to the Cloud, with Consent 1 1 1 1 1 1... Concept: shift data and processing to the device-side
Example: Centaurus - Edge Framework Expressive scripts specified as dataflows Operators transform raw data Models trained in cloud with big data set On Device: Intelligence Script Engine Context Scripts configure Operators Examples: Avg Band-Pass Naïve Bayes Segment Duration Entropy Min N-gram Std Dev Max Count Median Pattern Magnitude Match Tokenize Energy Difference Tokenize Decision FFT Tree Correlation Similarity Sum Euclidean Dist. Script for Watching a Movie Script for Walking Library of data Processors Example: Gyro Data FFT FFT of Gyro Modules to connect to data sources (sensors, logs, social networks)
Example: Centaurus - Edge Framework Quantifying savings: Walking Detection on smartphone 20 hours accelerometer @ 10Hz Implement with Centaurus - uploads only classification Implement in Cloud uploads all data Centaurus uploads only 0.14% of the data Centaurus time-to-classification is slightly faster Power consumption (network is biggest power hog): WLAN Upload Data Size (Kb) Power (mj) Time (ms) mj/kb Centaurus 27 148 237 0.97 Cloud-Only 55,487 66,827 84,788 0.42 HSPA Upload Data Size (Kb) Power (mj) Time (ms) mj/kb Centaurus 27 3069 2,896 64 Cloud-Only 55,487 1,048,766 545,826 15
The Next Step: Learning at the Edge Push training to the Edge, not just models Raw data never leaves the Edge! Challenges and brainstorming: 1) Decentralized learning: general + personal models Federated Learning Google Research Blog April 6, 2017 https://research.googleblog.com/2017/04/federated-learning-collaborative.html
The Next Step: Learning at the Edge Push training to the Edge, not just models Raw data never leaves the Edge! Challenges and brainstorming: 1) Decentralized learning: general + personal models 2) Adapting to varying device resources 3) Security and privacy between device and cloud 4) Supervised learning: soliciting user labels
The Next Step: Learning at the Edge Push training to the Edge, not just models Raw data never leaves the Edge! Challenges and brainstorming: 1) Decentralized learning: general + personal models 2) Adapting to varying device resources 3) Security and privacy between device and cloud 4) Supervised learning: soliciting user labels 5) Peer-to-Peer coordination at the Edge
Amazon Alexa Smart Home 200 Engineers and Scientists and growing fast Petabyte-scale data: millions of customers & devices Hiring Engineers and Scientists at all levels! Contact: evanwel@amazon.com