We are in the middle of the third wave of interest in artificial neural networks as the leading paradigm for machine learning. "ImageNet Classification with Deep...Jitendra Malik From Communications of the ACM | June 2017
In the 1980s backpropagation did not live up to the very high expectations of its advocates. Twenty years later, we know what went wrong: for deep neural networks...Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton From Communications of the ACM | June 2017
We describe DeepDive, a system that combines database and machine learning ideas to help to develop knowledge base construction systems.
Ce Zhang, Christopher Ré, Michael Cafarella, Christopher De Sa, Alex Ratner, Jaeho Shin, Feiran Wang, Sen Wu From Communications of the ACM | May 2017
"Exploiting Vector Instructions with Generalized Stream Fusion" points out that stream fusion by itself is not well suited for generating bulk instructions such...Guy Blelloch From Communications of the ACM | May 2017
Programmers should not have to sacrifice code clarity or good software engineering practices to obtain performance. This work shows how to attain this goal for...Geoffrey Mainland, Roman Leshchinskiy, Simon Peyton Jones From Communications of the ACM | May 2017
The authors of "Guilt-Free Data Reuse" show there is a way to construct a safety net that goes around a fixed dataset so that it may be analyzed interactively without...Jonathan Ullman From Communications of the ACM | April 2017
In this work, we initiate a principled study of how to guarantee the validity of statistical inference in adaptive data analysis.
Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, Omer Reingold, Aaron Roth From Communications of the ACM | April 2017
"Certifying a File System Using Crash Hoare Logic: Correctness in the Presence of Crashes" presents a big step toward real-world file systems that are crash-safe...Gernot Heiser From Communications of the ACM | April 2017
This paper introduces Crash Hoare logic, which extends traditional Hoare logic with a crash condition, a recovery procedure, and logical address spaces for specifying...Tej Chajed, Haogang Chen, Adam Chlipala, M. Frans Kaashoek, Nickolai Zeldovich, Daniel Ziegler From Communications of the ACM | April 2017
What is the most drastic way to reduce the cost of communication for parallel data processing algorithms? This is the question studied in "Reasoning on Data Partitioning...Leonid Libkin From Communications of the ACM | March 2017
We introduce a framework for reasoning about data partitioning to detect when we can avoid the data reshuffling step.
Tom J. Ameloot, Gaetano Geck, Bas Ketsman, Frank Neven, Thomas Schwentick From Communications of the ACM | March 2017
The authors of "Powering the Next Billion Devices with Wi-Fi" turn the problem of powering wireless sensor networks on its head. Instead of focusing on energy harvesting...Srinivasan Keshav From Communications of the ACM | March 2017
We present the first power over Wi-Fi system that delivers power to low-power sensors and devices and works with existing Wi-Fi chipsets.
Vamsi Talla, Bryce Kellogg, Benjamin Ransford, Saman Naderiparizi, Joshua R. Smith, Shyamnath Gollakota From Communications of the ACM | March 2017
We propose a new biometric based on the human body's response to an electric square pulse signal, called pulse-response.
Ivan Martinovic, Kasper Rasmussen, Marc Roeschlin, Gene Tsudik From Communications of the ACM | February 2017
One unfortunate fact about protocols is that as they get older and applied to more scenarios — and TLS is used basically everywhere — they tend to gain weight....Eric Rescorla From Communications of the ACM | February 2017
We systematically test popular TLS implementations and find unexpected transitions in many of their state machines that have stayed hidden for years. We show how...Benjamin Beurdouche, Karthikeyan Bhargavan, Antoine Delignat-Lavaud, Cédric Fournet, Markulf Kohlweiss, Alfredo Pironti, Pierre-Yves Strub, Jean Karim Zinzindohoue From Communications of the ACM | February 2017
"HACC: Extreme Scaling and Performance Across Diverse Architectures" describes the Hardware/Hybrid Accelerated Cosmology Code (HACC) framework, which uses a novel...Valentina Salapura From Communications of the ACM | January 2017
In this Research Highlight, we demonstrate the success of HACC on two very different machines, the CPU/GPU system Titan and the BG/Q systems Sequoia and Mira, attaining...Salman Habib, Vitali Morozov, Nicholas Frontiere, Hal Finkel, Adrian Pope, Katrin Heitmann, Kalyan Kumaran, Venkatram Vishwanath, Tom Peterka, Joe Insley, David Daniel, Patricia Fasel, Zarija Lukić From Communications of the ACM | January 2017
"Eulerian Video Magnification and Analysis" demonstrates that phase differences at a given frequency band, due to subtle motions in a video, can be independently...Richard Szeliski From Communications of the ACM | January 2017