Thursday, October 18, 2018
Submit your own News for
inclusion in our Site.
Click here...
Breaking News
How Google's Titan M Security Chip Works
Twitter Discloses Millions of State-backed Tweets and Accounts
Apple Releases Tool to Show You What Data it Has Collected
U.S. Broadcasters to Launch ATSC 3.0 TV In 2020
iPhone XR Available for pre-order on Friday
Facebook Sued Over Hiding Inflated Ad Metrics
Tesla Moves Closer to China With $2 billion Shanghai Gigafactory
Facebook is Reviving 'The Real World' Series
Active Discussions
Which of these DVD media are the best, most durable?
How to back up a PS2 DL game
Copy a protected DVD?
roxio issues with xp pro
Help make DVDInfoPro better with dvdinfomantis!!!
menu making
Optiarc AD-7260S review
cdrw trouble
 Home > News > General Computing > Google,...
Last 7 Days News : SU MO TU WE TH FR SA All News

Wednesday, May 02, 2018
Google, Baidu Support New MLPerf AI Benchmark

Google and Baidu collaborated with researchers at Harvard and Stanford to define a suite of benchmarks for machine learning (ML).

The 'MLPerf' effort aims to build a common set of benchmarks that enables the machine learning field to measure system performance for both training and inference from mobile devices to cloud services.

So far, AMD, Intel, two AI startups, and two other universities have expressed support for MLPerf, an initial version of which will be ready for use in August.

Other supporters include the University of California at Berkeley, the University of Minnesota, and the University of Toronto as well as two AI startups, SambaNova and Wave Computing.

The goals of MLPerf is to help companies and researchers accelerate progress in ML via fair and useful measurement. It will enable fair comparison of competing systems, enforce replicability to ensure reliable results while keeping benchmarking effort affordable so all can participate.

The first release of MLPerf will focus on training jobs on a range of systems from workstations to large data centers, a big pain point for web giants such as Baidu and Google. Later releases will expand to include inference jobs, eventually extended to include ones run on embedded client systems.

An early version of the suite running on a variety of AI frameworks will be ready to run in about three months.

Initially, MLPerf will measure the average time to train a model to a minimum quality, probably in hours. Given that these jobs are run on large banks of servers, it may not report performance per watt. It will take into consideration the costs of jobs as long as price does not vary over the time of day that they are run.

Nvidia's P100 Volta chip will be a reference standard because it is widely employed by data centers for training. The group aims to update published results every three months.

MLPerf will use two modes: A Closed Model Division specifies the model to be used and restricts the values of hyper parameters, e.g. batch size and learning rate, with the emphasis being on fair comparisons of the hardware and software systems. (The Sort equivalent is called "Daytona," alluding to the stock cars at the Daytona 500 mile race.)

In the MLPerf Open Model Division, competitors must solve the same problem using the same data set but with fewer restrictions, with the emphasis being on advancing the state-of-the-art of ML. (The Sort equivalent was called "Indy," alluding to the even faster Formula One custom race cars designed for events like the Indianapolis 500.)

Google Invests in Startups to Improve Google Assistant        All News        Samsung Releases PRO Endurance Memory Card
Google Invests in Startups to Improve Google Assistant     General Computing News      Nokia to Sell its Digital Health Business to Withings co-founder

Get RSS feed Easy Print E-Mail this Message

Related News
NVIDIA Introduces RAPIDS Software Platform for Large-Scale Data Analytics and Machine Learning
BrainChip Announces the Akida Architecture, a Neuromorphic System-on-Chip
Cisco Unveils Server for Artificial Intelligence and Machine Learning
Google Puts Machine Learning in the Hands of Advertisers
Samsung Wins at Two Top Global AI Machine Reading Comprehension Challenges
Google's Third Generation of Tensor Processing Unit Offers 100 Petaflops in Performance
IBM Sets Tera-scale Machine Learning Benchmark Record with POWER9 and GPUs
Making Music Using Sounds Generated With Machine Learning
Intel and Microsoft Enable AI Inference at the Edge with Intel Movidius Vision Processing Units on Windows ML
Arm's Project Trillium Offers Scalable, Machine Learning Compute Platform
IBM Scientists Demonstrate 10x Faster Machine Learning Using GPUs
Machine Learning Could Identify What You Are Typing On Skype By Recognizing Your Keyboard's Clicks

Most Popular News
Home | News | All News | Reviews | Articles | Guides | Download | Expert Area | Forum | Site Info
Site best viewed at 1024x768+ - CDRINFO.COM 1998-2018 - All rights reserved -
Privacy policy - Contact Us .