Approximate computing trades off computation quality with effort expended, and as rising
performance demands confront plateauing resource budgets, approximate computing has …

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and
study their effects on action recognition. Our motivation stems from the observation that 2D …

With the increasing popularity of the Internet of Things and massive Machine Type
Communication technologies, the number of connected devices is rising. However, although …

A number of recent efforts have attempted to design accelerators for popular machine
learning algorithms, such as those involving convolutional and deep neural networks (CNNs …

Advanced computing systems have long been enablers for breakthroughs in artificial
intelligence (AI) and machine learning (ML) algorithms, either through sheer computational …

Graphics Processing Units (GPUs) can accelerate diverse classes of applications, such as
recognition, gaming, data analytics, weather prediction, and multimedia. Many of these …

This paper introduces Input Responsive Approximation (IRA), an approach that uses a
canary input—a small program input carefully constructed to capture the intrinsic properties …

Approximate computing (AC) is an emerging computing paradigm suitable for intrinsic error-
tolerant applications to reduce energy consumption and execution time. Different …

Energy efficiency is a primary constraint in modern systems. Approximate computing is a
promising approach that trades quality of result for gains in efficiency and performance …

Machine learning has enabled significant benefits in diverse fields, but, with a few
exceptions, has had limited impact on computer architecture. Recent work, however, has …