tag: Harvard University

Flexible, Energy-Efficient Neural Network Processing At 16nm
By Geoff Tate - 06 Sep, 2018 - Comments: 0

At Hot Chips 30, held in August in Silicon Valley, Harvard University (Paul Whatmough, SK Lee, S Xi, U Gupta, L Pentecost, M Donato, HC Hseuh, Professor Brooks and Professor Gu) made a presentation on “SMIV: A 16nm SoC with Efficient and Flexible DNN Acceleration for Intelligent IOT Devices. ” (Their complete presentation is available now on the Hot Chips website for attendees and will be p... » read more

Power/Performance Bits: July 10
By Jesse Allen - 10 Jul, 2018 - Comments: 0

Heating up EV batteries Researchers from Pennsylvania State University developed a self-heating battery that can charge rapidly in cold conditions, a step they hope could spread adoption of electric vehicles. "Electric vehicles are popular on the west coast because the weather is conducive," said Xiao-Guang Yang, assistant research professor in mechanical engineering, Penn State. "Once you ... » read more

Manufacturing Bits: May 29
By Ed Sperling - 29 May, 2018 - Comments: 0

Utilizing Heat For Energy One of the big problems in electronics in general, and semiconductors particular, is heat. And it's not just about leakage current anymore. Heat is a problem at every level, from circuit design to the materials being used inside the chips, as well as warpage between die caused by heat after they are packaged together. Heat can prematurely age chips as well as destroy ... » read more

System Bits: March 27
By Ann Mutschler - 27 Mar, 2018 - Comments: 0

New quantum electronic material has atomic structure resembling a Japanese basketweaving pattern According to MIT, Harvard University, and Lawrence Berkeley National Laboratory researchers, a motif of Japanese basketweaving known as the kagome pattern has preoccupied physicists for decades. They reminded that kagome baskets are typically made from strips of bamboo woven into a highly symmetric... » read more

SM2: A Deep Neural Network Accelerator In 28nm
By Flex Logix - 28 Feb, 2018 - Comments: 0

Deep learning algorithms present an exciting opportunity for efficient VLSI implementations due to several useful properties: (1) an embarrassingly parallel dataflow graph, (2) significant sparsity in model parameters and intermediate results, and (3) resilience to noisy computation and storage. Exploiting these characteristics can offer significantly improved performance and energy efficiency.... » read more

System Bits: Feb. 20
By Ann Mutschler - 20 Feb, 2018 - Comments: 0

An evolution in electronics Restoring some semblance to those who have lost the sensation of touch has been a driving force behind Stanford University chemical engineer Zhenan Bao’s decades-long quest to create stretchable, electronically-sensitive synthetic materials. [caption id="attachment_24131783" align="aligncenter" width="300"] Zhenan Bao, the K.K. Lee professor of chemical engineer... » read more

The Race To Accelerate
By Ed Sperling - 12 Feb, 2018 - Comments: 1

Geoff Tate, CEO of [getentity id="22921" e_name="Flex Logix"], sat down with Semiconductor Engineering to discuss how the chip industry is changing, why that bodes well for embedded FPGAs, and what you need to be aware of when using programmable logic on the same die as other devices. What follows are excerpts of that conversation. SE: What are the biggest challenges facing the chip industry... » read more

System Bits: Aug. 15
By Ann Mutschler - 15 Aug, 2017 - Comments: 0

Machine-learning system for smoother streaming To combat the frustration of video buffering or pixelation, researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed “Pensieve,” an artificial intelligence system that uses machine learning to pick different algorithms depending on network conditions thereby delivering a higher-quality streaming exp... » read more

The Week In Review: IoT
By Jeff Dorsch - 04 Aug, 2017 - Comments: 0

Legislation Four senators plan to introduce a bipartisan bill that would require federal government vendors to provide Internet-connected devices and equipment that is patchable and conforms to industry cybersecurity standards. Such products must not have unchangeable passwords or known security vulnerabilities. The bill was drafted with expert advice from the Atlantic Council and Harvard Univ... » read more

System Bits: July 18
By Ann Mutschler - 18 Jul, 2017 - Comments: 0

Melanoma predicted from images with a high degree of accuracy by neural network model The poke and punch of traditional melanoma biopsies could be avoided in the near future, thanks to work by UC Santa Barbara researchers. UCSB undergrad Abhishek Bhattacharya is using the power of artificial intelligence to help people ascertain whether that new and strange mark is, in fact, the deadly skin... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2025 SMG   |  Terms of Service  |  Privacy Policy