tag: neural networks

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

The Week In Review: Design
By Jesse Allen - 22 Dec, 2017 - Comments: 0

Altium released the latest version of its PCB design suite. Improvements include a new interface and an upgrade to 64-bit architecture combined with multi-threaded task optimizations. Other additions include a new BoM rule checker and length tuning and pin-swapping in the user-guided routing engine. Creonic announced a new line of IP for 5G forward error correction. The product line covers t... » read more

System Bits: Dec. 12
By Ann Mutschler - 12 Dec, 2017 - Comments: 0

Increasing performance scaling with packageless processors Demand for increasing performance is far outpacing the capability of traditional methods for performance scaling. Disruptive solutions are needed to advance beyond incremental improvements. Traditionally, processors reside inside packages to enable PCB-based integration. However, a team of researchers from the Department of Electrical ... » read more

Power/Performance Bits: Nov 28
By Linda Christensen - 28 Nov, 2017 - Comments: 0

Deep learning to detect nuclear reactor cracks Inspecting nuclear power plant components for cracks is critical to preventing leaks, as well as to control in maintenance costs. But the current vision-based crack detection approaches are not very effective. Moreover, they are prone to human error, which in the case of nuclear power can be disastrous. To address this problem, Purdue Universit... » read more

Software Framework Requirements For Embedded Vision
By Gordon Cooper - 09 Nov, 2017 - Comments: 0

Deep learning techniques such as convolutional neural networks (CNN) have significantly increased the accuracy—and therefore the adoption rate—of embedded vision for embedded systems. Starting with AlexNet’s win in the 2012 ImageNet Large Scale Visual Recognition Challenge (ILSVRC), deep learning has changed the market by drastically reducing the error rates for image classification and d... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2024 SMG   |  Terms of Service  |  Privacy Policy