Page 27 - MSDN Magazine, July 2018

desktop machine, and installation consists of building C/C++ source code—there’s no .msi installer for ELL (yet).
A cool feature of ELL that isn’t obvious is that it performs some very sophisticated optimization behind the scenes. For example, the ELL team has explored ways to compress large ML models, including sparsification and pruning techniques, and replacing floating point math with 1-bit math. The ELL team is also looking at algorithms that can be used in place of neural networks, includ- ing improved decision trees and k-DNF classifiers.
The tutorials on the ELL Web site are quite good, but because there are many steps involved, they are a bit long. Let me briefly sketch out the process so you can get a feel for what installing and using ELL is like. Note that my commands are not syntactically correct; they’re highly simplified to keep the main ideas clear.
Installing the ELL system resembles:
> (install several tools such as cmake and BLAS)
> git clone https://github.com/Microsoft/ELL.git
> cd ELL
> nuget.exe restore external/packages.config -PackagesDirectory external > md build
> cd build
> cmake -G "Visual Studio 15 2017 Win64" ..
> cmake --build . --config Release
> cmake --build . --target _ELL_python --config Release
In words, you must have quite a few tools installed before start- ing, then you pull the ELL source code down from GitHub and then build the ELL executable tools and Python binding using cmake.
Creating an ELL model resembles:
> python cntk_import.py iris_cntk.model
> python wrap.py iris_nn_cntk.ell --language python --target host
> cd host
> md build
> cd build
> cmake -G "Visual Studio 15 2017 Win64" .. && cmake --build . --config release
That is, you use ELL tool cntk_import.py to create a .ell file from a CNTK model file. You use wrap.py to generate a lot of C/C++ specific to a particular target IoT device. And you use cmake to generate executables that encapsulate the original trained ML model’s behavior.
Wrapping Up
To summarize, a machine learning model is all the information needed for a software system to accept input and generate a pre- diction. Because IoT devices on the edge often require very fast and reliable performance, it’s sometimes necessary to compute ML pre- dictions directly on a device. However, IoT devices are often small and weak, so you can’t simply copy a model that was developed on a powerful desktop machine to the device. A standard approach is to write custom C/C++ code, but this approach doesn’t scale to complex ML models. An emerging approach is the use of ML cross-compilers, such as the Microsoft Embedded Learning Library.
When fully mature and released, the ELL system will quite likely make developing complex ML models for IoT devices on the edge dramatically easier than it is today. n
Dr. James mccaffrey works for Microsoft Research in Redmond, Wash. He has worked on several Microsoft products, including Internet Explorer and Bing. Dr. McCaffrey can be reached at jamccaff@microsoft.com.
Thanks to the following Microsoft technical experts who reviewed this article: Byron Changuion, Chuck Jacobs, Chris Lee and Ricky Loynd
msdnmagazine.com
®
Instantly Search Terabytes
dtSearch’s document filters support: • popular file types
• emails with multilevel attachments • a wide variety of databases
• web data
Over 25 search options including:
• efficient multithreaded search •
• forensics options like credit card search
• SDKs for Windows, UWP, Linux, Mac, iOS in beta, Android in beta
• FAQs on faceted search, granular data classification, Azure and more
Visit dtSearch.com for
• hundreds of reviews and case studies
• fully-functional enterprise and developer evaluations
The Smart Choice for Text Retrieval® since 1991
easy
multicolor
hit-
highlighting
Developers:
• APIs for .NET, C++ and Java; ask about new cross-platform .NET Standard SDK with Xamarin and .NET Core
dtSearch.com 1-800-IT-FINDS