Communications of the ACM
Latest Research
From Communications of the ACM
Technical Perspective: Why Don't Today's Deep Nets Overfit to Their Training Data?
"Understanding Deep Learning (Still) Requires Rethinking Generalization," Chiyuan Zhang, et al., brings a fundamental new theoretical challenge: Why don't today's...
From Communications of the ACM
Understanding Deep Learning (Still) Requires Rethinking Generalization
In this work, we presented a simple experimental framework for interrogating purported measures of generalization.
From Communications of the ACM
Technical Perspective: XNOR-Networks – Powerful but Tricky
How to produce a convolutional neural net that is small enough to run on a mobile device, and accurate enough to be worth using? The strategies in "Enabling AI...
From Communications of the ACM
Enabling AI at the Edge with XNOR-Networks
We present a novel approach to running state-of-the-art AI algorithms in edge devices, and propose two efficient approximations to standard convolutional neural...
From Communications of the ACM
Technical Perspective: When the Adversary Is Your Friend
The key insight of the "Generative Adversarial Networks," by Ian Goodfellow et al., is to learn a generative model's loss function at the same time as learning...
From Communications of the ACM
Generative Adversarial Networks
In this overview paper, we describe one particular approach to unsupervised learning via generative modeling called generative adversarial networks. We briefly...
From Communications of the ACM
Technical Perspective: Progress in Spatial Computing for Flood Prediction
There are few algorithms for multi-flow graphs beyond flow accumulation. The authors of "Flood-Risk Analysis on Terrains" take a big step to fill this knowledge...
From Communications of the ACM
Flood-Risk Analysis on Terrains
In this paper, we study a number of flood-risk related problems, give an overview of efficient algorithms for them, as well as explore the efficacy and efficiency...
From Communications of the ACM
Technical Perspective: Computing the Value of Location Data
"Computing Value of Spatiotemporal Information," by Heba Aly et al., describes a technique for computing the monetary value of a person's location data for a potential...
From Communications of the ACM
Computing Value of Spatiotemporal Information
We investigate the intrinsic value of location data in the context of strong privacy, where location information is only available from end users via purchase. ...
From Communications of the ACM
Technical Perspective: Entity Matching with Magellan
Magellan's key insight is that a successful entity matching system must offer a versatile system building paradigm for entity matching that can be easily adapted...
From Communications of the ACM
Magellan: Toward Building Ecosystems of Entity Matching Solutions
Entity matching can be viewed as a special class of data science problems and thus can benefit from system building ideas in data science.
From Communications of the ACM
Technical Perspective: Algorithm Selection as a Learning Problem
"Data-Driven Algorithm Design," by Rishi Gupta and Tim Roughgarden, addresses the issue that the best algorithm to use for many problems depends on what the input...
From Communications of the ACM
Data-Driven Algorithm Design
We model the problem of identifying a good algorithm from data as a statistical learning problem.
From Communications of the ACM
Technical Perspective: An Answer to Fair Division's Most Enigmatic Question
The envy-free cake-cutting problem stood its ground for two decades, until it was cracked by Aziz and Mackenzie. Their solution is presented in "A Bounded and Envy...
From Communications of the ACM
A Bounded and Envy-Free Cake Cutting Algorithm
We report on our algorithm that resolved the well-studied cake cutting problem in which the goal is to find an envy-free allocation of a divisible resource based...
From Communications of the ACM
Technical Perspective: Lighting the Way to Visual Privacy
"Automating Visual Privacy Protection Using a Smart LED," presents a new technique to address the issue of cameras capturing proprietary or private information—it...
From Communications of the ACM
Automating Visual Privacy Protection Using a Smart LED
We introduce LiShield, which automatically protects a physical scene against photographing, by illuminating it with smart LEDs flickering in specialized waveforms...
From Communications of the ACM
Technical Perspective: A Whitebox Solution for Blackbox-Like Behaviors
DeepXplore brings a software testing perspective to deep neural networks and, in doing so, creates the opportunity for enormous amounts of follow-on work in several...
From Communications of the ACM