An adaptive synaptic array using Fowler–Nordheim dynamic analog memory


Abstract "In this paper we present an adaptive synaptic array that can be used to improve the energy-efficiency of training machine learning (ML) systems. The synaptic array comprises of an ensemble of analog memory elements, each of which is a micro-scale dynamical system in its own right, storing information in its temporal state trajectory. The state trajectories are then modulated by a sys... » read more

Research Bits: March 29


Brain-like AI chip Researchers from Purdue University, Santa Clara University, Portland State University, Pennsylvania State University, Argonne National Laboratory, University of Illinois Chicago, Brookhaven National Laboratory, and University of Georgia built a reprogrammable chip that could be used as the basis for brain-like AI hardware. “The brains of living beings can continuously l... » read more

Technical Paper Round-Up: March 29


Improving batteries, ultra low-power photonic edge computing, SLAM, Tellurium for 2D semiconductors, and reservoir computing top the past week's technical papers. The focus on energy is critical as the edge buildout continues and more devices are connected to a battery, while research into new architectures and materials that will continue scaling and improve performance per watt continue at th... » read more

Fuzz, Penetration, and AI Testing for SoC Security Verification: Challenges and Solutions


Abstract "The ever-increasing usage and application of system-on-chips (SoCs) has resulted in the tremendous modernization of these architectures. For a modern SoC design, with the inclusion of numerous complex and heterogeneous intellectual properties (IPs),and its privacy-preserving declaration, there exists a wide variety of highly sensitive assets. These assets must be protected from any u... » read more

Improving Memory Efficiency And Performance


This is the second of two parts on CXL vs. OMI. Part one can be found here. Memory pooling and sharing are gaining traction as ways of optimizing existing resources to handle increasing data volumes. Using these approaches, memory can be accessed by a number of different machines or processing elements on an as-needed basis. Two protocols, CXL and OMI, are being leveraged to simplify thes... » read more

Native lattice strain induced structural earthquake in sodium layered oxide cathodes (batteries)


Abstract "High-voltage operation is essential for the energy and power densities of battery cathode materials, but its stabilization remains a universal challenge. To date, the degradation origin has been mostly attributed to cycling-initiated structural deformation while the effect of native crystallographic defects induced during the sophisticated synthesis process has been significantly ove... » read more

SolidPAC is an interactive battery-on-demand energy density estimator for solid-state batteries


Summary "Solid-state batteries hold the promise to be highly impactful next-generation technologies for high-energy and -power-density rechargeable battery applications. It is crucial to identify the metrics that an emerging battery technology should fulfill to achieve parity with conventional Li-ion batteries, primarily in terms of energy density. However, limited approaches exist today to as... » read more

Bell state analyzer for spectrally distinct photons


Abstract "We demonstrate a Bell state analyzer that operates directly on frequency mismatch. Based on electro-optic modulators and Fourier-transform pulse shapers, our quantum frequency processor design implements interleaved Hadamard gates in discrete frequency modes. Experimental tests on entangled-photon inputs reveal fidelities of ∼98% for discriminating between the |Ψ+⟩ and |Ψ−⟩... » read more

Experimental photonic quantum memristor


Abstract "Memristive devices are a class of physical systems with history-dependent dynamics characterized by signature hysteresis loops in their input–output relations. In the past few decades, memristive devices have attracted enormous interest in electronics. This is because memristive dynamics is very pervasive in nanoscale devices, and has potentially groundbreaking applications ranging... » read more

Wavelength Multiplexed Ultralow-Power Photonic Edge Computing


Abstract "Advances in deep neural networks (DNNs) are transforming science and technology. However, the increasing computational demands of the most powerful DNNs limit deployment on low-power devices, such as smartphones and sensors -- and this trend is accelerated by the simultaneous move towards Internet-of-Things (IoT) devices. Numerous efforts are underway to lower power consumption, but ... » read more

← Older posts Newer posts →