Menu
AWS and Microsoft combine to drive deep learning in the cloud

AWS and Microsoft combine to drive deep learning in the cloud

An AWS and Microsoft joint effort makes neural networks easier to program and use with the MXNet and Microsoft Cognitive Toolkit frameworks

Satya Nadella (Microsoft) and Jeff Bezos (AWS)

Satya Nadella (Microsoft) and Jeff Bezos (AWS)

Deep learning systems have long been tough to work with, due to all the fine-tuning and knob-twiddling needed to get good results from them. Gluon is a joint effort by Amazon Web Services (AWS) and Microsoft to reduce all that fiddling effort.

Gluon works with the Apache MXNet and Microsoft’s Cognitive Toolkit frameworks to optimise deep-learning network training on those systems.

How Gluon works

Neural networks, like those used in deep learning systems, work in roughly three phases:

  1. The developer hard-codes the behaviour of the network
  2. The developer adjusts how the data is weighted and handled by the network, by changing settings to produce useful results
  3. The finished network is used to serve predictions

The problem with steps one and two is that they’re tedious and inflexible. Hard-coding a network is slow, and altering that coding to improve the network’s behavior is also slow. Likewise, figuring out the best weights to use in a network is a task ripe for automation.

Gluon offers a way to write neural networks that are defined more like datasets than code. A developer can instantiate a network declaratively, using common patterns like chains of neural network layers.

In addition, Gluon code is meant to be easy to write and easy to comprehend, and it takes advantage of native features in the language used (for example, Python’s context managers).

Where Gluon helps developers

The most basic way Gluon helps the developer is by making it easier to both define a network and modify it.

In Gluon, a neural network can be described in the conventional way, with a block of code that doesn’t change. But the network can also be described as if it were a data structure, so it can be altered on the fly to accommodate changes during the training.

Code written in Gluon can take advantage of GPU-accelerated and distributed processing features in both MXNet and Cognitive Toolkit, so training jobs can be distributed across multiple nodes. Its creators say Gluon can do that without any performance compromises compared to the maual approach.

Where you can use Gluon

Gluon works today with MXNet. The Python 0.11 and later front ends for MXNet, for example, have Gluon library support. Gluon also works transparently with both MXNet’s GPU-accelerated edition and the Intel Math Kernel Library extensions for speeding CPU-bound processing.

Microsoft has not yet released a version of the Microsoft Cognitive Toolkit with Gluon support. It promises Gluon support in a future release of the toolkit.

This article originally appeared on InfoWorld.


Follow Us

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.

Tags CloudMicrosoftGooglemicrosoft azureAmazon Web ServicesAWSGoogle Cloudmachine learningdeep learningGluon

Featured

Slideshows

Leading female front runners of the Kiwi ICT industry honoured at 2019 WIICTA

Leading female front runners of the Kiwi ICT industry honoured at 2019 WIICTA

Reseller News has honoured the leading female front runners of the New Zealand ICT industry at the 2019 Women in ICT Awards (WIICTA) in Auckland. The awards recognised standout individuals across six categories, spanning Entrepreneur, Rising Star, Shining Star, Community, Technical and Achievement. Photos by Gino Demeer.

Leading female front runners of the Kiwi ICT industry honoured at 2019 WIICTA
Reseller News kicks off awards season in 2019 with Judges' Lunch

Reseller News kicks off awards season in 2019 with Judges' Lunch

The 2019 Reseller News Innovation Awards has kicked off with the Judges Lunch in Auckland with 70 judges in the voting panel. The awards will reflect the changing dynamics of the channel, recognising excellence across customer value and innovation - spanning start-ups, partners, distributors and vendors. Photos by Christine Wong.

Reseller News kicks off awards season in 2019 with Judges' Lunch
Reseller News welcomes industry figures for 2019 Hall of Fame lunch

Reseller News welcomes industry figures for 2019 Hall of Fame lunch

Reseller News welcomed 2018 inductees - Chris Simpson, Kendra Ross and Phill Patton - to the third running of the Reseller News Hall of Fame lunch, held at the French Cafe in Auckland. The inductees discussed the changing landscape of the technology industry in New Zealand, while outlining ways to attract a new breed of players to the ecosystem. Photos by Gino Demeer.

Reseller News welcomes industry figures for 2019 Hall of Fame lunch
Show Comments