中文 English

Graphene-based PUFs that are reconfigurable and resilient to ML attacks


Researchers at Pennsylvania State University propose using graphene to create physically unclonable functions (PUFs) that are energy efficient, scalable, and secure against AI attacks. Abstract "Graphene has a range of properties that makes it suitable for building devices for the Internet of Things. However, the deployment of such devices will also likely require the development of s... » read more

Tailoring spatial entropy in EUV focused beams for multispectral ptychography


The Advanced Research Center for Nanolithography (ARCNL) and Vrije Universiteit Amsterdam have developed a new class of diffractive optical elements that paves the way towards more widespread use of EUV microscopy. Abstract "Diffractive optics can be used to accurately control optical wavefronts, even in situations where refractive components such as lenses are not available. For instance, c... » read more

Electrically connected spin-torque oscillators array for 2.4 GHz WiFi band transmission and energy harvesting


Researchers at the National University of Singapore and Tohoku University developed a device that uses spin-torque oscillators (STOs) to harvest energy from 2.4GHz Wi-Fi signals and wirelessly power an LED without need for a battery.   Technical Paper Link: Abstract "The mutual synchronization of spin-torque oscillators (STOs) is critical for communication, energy harvesting ... » read more

Multistep staircase avalanche photodiodes with extremely low noise & deterministic amplification (lidar)


Engineers at University of Texas at Austin and University of Virginia developed a light detector that can amplify weak light signals and reduce noise to improve the accuracy of lidar. Find technical paper here. Abstract "In 1982, Capasso and co-workers proposed the solid-state analogue of the photomultiplier tube, termed the staircase avalanche photodiode. Through a combination of co... » read more

Emergent magnetic monopoles isolated using quantum-annealing computer


Using D-Wave’s quantum-annealing computer, Los Alamos National Laboratory has shown that it’s possible to isolate magnetic monopoles. This research could one day enable future nanomagnets.   Abstract: "Artificial spin ices are frustrated spin systems that can be engineered, wherein fine tuning of geometry and topology has allowed the design and characterization of exotic eme... » read more

HyperRec: Efficient Recommender Systems with Hyperdimensional Computing


A group of researchers are taking a different approach to AI. The University of California at San Diego, the University of California at Irvine, San Diego State University and DGIST recently presented a paper on a new hardware algorithm based on hyperdimensional (HD) computing, which is a brain-inspired computing model. The new algorithm, called HyperRec, uses data that is modeled with bina... » read more

Accellera’s Functional Safety Group White Paper


"The objective of the Functional Safety Working Group is to standardize information for capturing and propagating the safety intent from the system down to the SoC / IP design and implementation including failure mode propagation, verification, validation, reliability and Safety Mechanisms. The safety intent standardization will support data exchange and traceability across different safety ana... » read more

Ferroelectric, hafnium oxide based transistors for digital beyond von-Neumann computing


Source: AIP Applied Physics Letters, published 2/4/2021.  Evelyn T. Breyer1,  Halid Mulaosmanovic1,  Thomas Mikolajick1,2, and  Stefan Slesazeck1 1Nanoelectronic Materials Laboratory (NaMLab) gGmbH, 01187 Dresden, Germany 2Chair of Nanoelectronics, TU Dresden, 01187 Dresden, Germany   Technical paper link is here » read more

Final Report: National Security Commission on AI


  In August 2018, Section 1051 of the John S. McCain National Defense Authorization Act for Fiscal Year 2019 established the National Security Commission on Artificial Intelligence as an independent Commission “to consider the methods and means necessary to advance the development of artificial intelligence, machine learning, and associated technologies to comprehensively address the... » read more

Enabling Efficient and Flexible FPGA Virtualization for Deep Learning in the Cloud


SOURCE: Shulin Zeng, Guohao Dai, Hanbo Sun, Kai Zhong, Guangjun Ge, Kaiyuan Guo, Yu Wang, Huazhong Yang(Tsinghua University, Beijing, China).  Published on arXiv:2003.12101 [cs.DC])   ABSTRACT: "FPGAs have shown great potential in providing low-latency and energy-efficient solutions for deep neural network (DNN) inference applications. Currently, the majority of FPGA-based DNN accel... » read more

← Older posts