arXiv Analytics

Sign in

arXiv:1612.07625 [cs.CV]AbstractReferencesReviewsResources

Hardware for Machine Learning: Challenges and Opportunities

Vivienne Sze, Yu-Hsin Chen, Joel Emer, Amr Suleiman, Zhengdong Zhang

Published 2016-12-22Version 1

Machine learning plays a critical role in extracting meaningful information out of the zetabytes of sensor data collected every day. For some applications, the goal is to analyze and understand the data to identify trends (e.g., surveillance, portable/wearable electronics); in other applications, the goal is to take immediate action based the data (e.g., robotics/drones, self-driving cars, smart Internet of Things). For many of these applications, local embedded processing near the sensor is preferred over the cloud due to privacy or latency concerns, or limitations in the communication bandwidth. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to throughput and accuracy requirements. Furthermore, flexibility is often required such that the processing can be adapted for different applications or environments (e.g., update the weights and model in the classifier). In many applications, machine learning often involves transforming the input data into a higher dimensional space, which, along with programmable weights, increases data movement and consequently energy consumption. In this paper, we will discuss how these challenges can be addressed at various levels of hardware design ranging from architecture, hardware-friendly algorithms, mixed-signal circuits, and advanced technologies (including memories and sensors).

Related articles: Most relevant | Search more
arXiv:2007.07221 [cs.CV] (Published 2020-06-27)
Alpha-Net: Architecture, Models, and Applications
arXiv:1901.07387 [cs.CV] (Published 2019-01-18)
A Recent Survey on the Applications of Genetic Programming in Image Processing
arXiv:1904.02587 [cs.CV] (Published 2019-04-04)
Geometry of the Hough transforms with applications to synthetic data