DL End-user Policy
Users of the ACM Digital Library are asked to abide by the ACM Author Rights and Publishing Policy, paying particular attention to the permissions statement.
You may make digital or hard copies of the individual articles that you are entitled to access for personal or classroom use, as long as the copies are not sold to the students and they bear the appropriate ACM copyright or license notice. You may assemble and distribute links that point to works in the ACM Digital Library.
Do not republish these ACM works, or post them on other servers, or redistribute them to lists, without first getting explicit permission from ACM. Contact email@example.com. Please do not abuse your access rights to the ACM Digital Library by wholesale duplication of all or substantial sections of the ACM Digital Library.
Do not use robots or intelligent agents: they degrade the performance of the system for everyone, and are not a proper use of the ACM Digital Library. ACM reserves the right to suspend, or even cancel your subscription, if systematic downloading is discovered. ACM also reserves the right to block access to the Digital Library for IP addresses from where such activities are found to be originating. For a full statement of institutional, librarian, and individual usage rights, see: Digital Library Usage Policies
Written by leading domain experts for software engineers, ACM Case Studies provide an in-depth look at how software teams overcome specific challenges by implementing new technologies, adopting new practices, or a combination of both. Often through first-hand accounts, these pieces explore what the challenges were, the tools and techniques that were used to combat them, and the solution that was achieved.
ACM Queue’s “Research for Practice” is your number one resource for keeping up with emerging developments in the world of theory and applying them to the challenges you face on a daily basis. In this installment, Dan Crankshaw and Joey Gonzalez provide an overview of machine learning server systems. What happens when we wish to actually deploy a machine learning model to production, and how do we serve predictions with high accuracy and high computational efficiency? Dan and Joey’s curated research selection presents cutting-edge techniques spanning database-level integration, video processing, and prediction middleware. Given the explosion of interest in machine learning and its increasing impact on seemingly every application vertical, it's possible that systems such as these will become as commonplace as relational databases are today.