"WINOGRANDE" explores new methods of dataset development and adversarial filtering, expressly designed to prevent AI systems from making claims of smashing through...Leora Morgenstern From Communications of the ACM | September 2021
We introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original Winograd Schema Challenge, but adjusted to improve both the scale and the...Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi From Communications of the ACM | September 2021
"Optimal Auctions Through Deep Learning," by Paul Dütting et al., contributes a very interesting and forward-looking new take on the optimal multi-item mechanism...Constantinos Daskalakis From Communications of the ACM | August 2021
We overview recent research results that show how tools from deep learning are shaping up to become a powerful tool for the automated design of near-optimal auctions...Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, Sai S. Ravindranath From Communications of the ACM | August 2021
"Deriving Equations from Sensor Data Using Dimensional Function Synthesis," by Vasileios Tsoutsouras, et al., addresses the key problem of discovering relationships...Sriram Sankaranarayanan From Communications of the ACM | July 2021
We present a new method, which we call dimensional function synthesis, for deriving functions that model the relationship between multiple signals in a physical...Vasileios Tsoutsouras, Sam Willis, Phillip Stanley-Marbell From Communications of the ACM | July 2021
"In-Sensor Classification With Boosted Race Trees," by Georgios Tzimpragos, et al., proposes a surprising, novel, and creative approach to post-Moore's Law computing...Abhishek Bhattacharjee From Communications of the ACM | June 2021
We demonstrate the potential of a novel form of encoding, race logic, in which information is represented as the delay in the arrival of a signal.
Georgios Tzimpragos, Advait Madhavan, Dilip Vasudevan, Dmitri Strukov, Timothy Sherwood From Communications of the ACM | June 2021
"Simba," by Yakun Sophia Shao, et al., presents a scalable deep learning accelerator architecture that tackles issues ranging from chip integration technology to...Natalie Enright Jerger From Communications of the ACM | June 2021
This work investigates and quantifies the costs and benefits of using multi-chip-modules with fine-grained chiplets for deep learning inference, an application...Yakun Sophia Shao, Jason Cemons, Rangharajan Venkatesan, Brian Zimmer, Matthew Fojtik, Nan Jiang, Ben Keller, Alicia Klinefelter, Nathaniel Pinckney, Priyanka Raina, Stephen G. Tell, Yanqing Zhang, William J. Dally, Joel Emer, C. Thomas Gray, Brucek Khailany, Stephen W. Keckler From Communications of the ACM | June 2021
"Understanding Deep Learning (Still) Requires Rethinking Generalization," Chiyuan Zhang, et al., brings a fundamental new theoretical challenge: Why don't today's...Sanjeev Arora From Communications of the ACM | March 2021
In this work, we presented a simple experimental framework for interrogating purported measures of generalization.
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals From Communications of the ACM | March 2021
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...David Alexander Forsyth From Communications of the ACM | December 2020
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...Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi From Communications of the ACM | December 2020
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...Alexei A. Efros, Aaron Hertzmann From Communications of the ACM | November 2020
In this overview paper, we describe one particular approach to unsupervised learning via generative modeling called generative adversarial networks. We briefly...Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio From Communications of the ACM | November 2020
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...Wang-Chiew Tan From Communications of the ACM | August 2020
Entity matching can be viewed as a special class of data science problems and thus can benefit from system building ideas in data science.
AnHai Doan, Pradap Konda, Paul Suganthan G. C., Yash Govind, Derek Paulsen, Kaushik Chandrasekhar, Philip Martinkus, Matthew Christie From Communications of the ACM | August 2020
"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...Avrim Blum From Communications of the ACM | June 2020