tag: neural networks

Packing Neural Networks Into End-User Client Devices
By Arm - 04 Apr, 2018 - Comments: 0

Most of today’s neural networks can only run on high-performance servers. There’s a big push to change this and simplify network processing to the point where the algorithms can run on end-user client devices. One approach is to eliminate complexity by replacing floating-point representation with fixed-point representation. We take a different approach, and recommend a mix of the two, so as... » read more

AI: The Next Big Thing
By Ed Sperling - 15 Mar, 2018 - Comments: 2

The next big thing isn't actually a thing. It's a set of finely tuned statistical models. But developing, optimizing and utilizing those models, which collectively fit under the umbrella of artificial intelligence, will require some of the most advanced semiconductors ever developed. The demand for artificial intelligence is almost ubiquitous. As with all "next big things," it is a horizonta... » read more

Power/Performance Bits: Mar. 6
By Jesse Allen - 06 Mar, 2018 - Comments: 0

Neural network chip Neural networks are both slow and consume a lot of power. This made researchers at MIT examine the important aspects of the nodes within a neural network and to see how each part of the computation could be improved. The outcome was a dedicated chip that increases the speed of neural-network computations by three to seven times over its predecessors, while reducing power c... » read more

Verification Of Functional Safety (Part 2)
By Brian Bailey - 22 Feb, 2018 - Comments: 0

The automotive industry is grappling with a tradeoff between cost and safety. Safety is well understood in industries that are cost-insensitive, such as aerospace and medical, and the consumer industry has a long track record of driving down costs while increasing functionality. But can these two industries be brought together in a safe and effective manner to enable automobiles to achieve the ... » read more

System Bits: Feb. 13
By Ann Mutschler - 13 Feb, 2018 - Comments: 0

Enabling individual manufacturing apps Researchers at the Fraunhofer Institute for Computer Graphics Research IGD focused on Industrie 4.0 recognize that manufacturing is turning toward batch sizes of one and individualized production in what is sometimes referred to as ‘highly customized mass production.’ [caption id="attachment_24131609" align="aligncenter" width="300"] The scanning ... » read more

Not All Ops Are Created Equal
By Arm - 07 Feb, 2018 - Comments: 0

Efficient and compact neural network models are essential for enabling the deployment on mobile and embedded devices. In this work, we point out that typical design metrics for gauging the efficiency of neural network architectures – total number of operations and parameters – are not sufficient. These metrics may not accurately correlate with the actual deployment metrics such as energy an... » read more

Blog Review: Jan. 24
By Jesse Allen - 24 Jan, 2018 - Comments: 0

Mentor's Rich Edelman shares some tips for debugging complex UVM testbenches containing multiple agents, multiple checkers, and new HDL. Synopsys' Prasad Subudhi K. S. explains the PCIe PIPE 4.4.1 specification and the major improvements since 4.3, including better optimization in data flow and ultra-low power operations. Cadence's Paul McLellan steps back to before the Meltdown and Spect... » read more

Blog Review: Jan. 17
By Jesse Allen - 17 Jan, 2018 - Comments: 0

Mentor's Puneet Sinha identifies the key challenges, along with cost reduction and optimization opportunities, that come with using electric powertrains in autonomous vehicles. Synopsys' Robert Vamosi examines the impact of limited cellular networks on autonomous cars, and new communications protocols that could address coverage gaps. Cadence's Paul McLellan listens in as Lucian Shifren o... » read more

Machine Learning’s Growing Divide
By Brian Bailey - 11 Jan, 2018 - Comments: 7

[getkc id="305" kc_name="Machine learning"] is one of the hottest areas of development, but most of the attention so far has focused on the cloud, algorithms and GPUs. For the semiconductor industry, the real opportunity is in optimizing and packaging solutions into usable forms, such as within the automotive industry or for battery-operated consumer or [getkc id="76" kc_name="IoT"] products. ... » read more

The Future Of AI Is In Materials
By Sundeep Bajikar - 09 Jan, 2018 - Comments: 0

I had the pleasure of hosting an eye-opening presentation and Q&A with Dr. Jeff Welser of IBM at a recent Applied Materials technical event in San Francisco. Dr. Welser is Vice President and Director of IBM Research's Almaden lab in San Jose. He made the case that the future of hardware is AI. At Applied Materials we believe that advanced materials engineering holds the keys to unlocking... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

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