Results 41 to 50 of about 2,053 (144)

Neuromorphic Photonic Processing and Memory With Spiking Resonant Tunneling Diode Neurons and Neural Networks

Advanced Intelligent Systems, EarlyView.
This work shows resonant tunneling diode‐based opto‐electronic spiking neurons enabling fast edge detection in time series, a two‐layer photonic spiking neural network for complex classification, and a depth‐tunable photonic spiking memory system. Neuromorphic computing—modeled after the functionality and efficiency of biological neural systems—offers ...
Dafydd Owen‐Newns, Joshua Robertson, Giovanni Donati, Qusay Al‐Taai, José Figueiredo, Edward Wasige, Kathy Lüdge, Bruno Romeira, Antonio Hurtado   +8 more
wiley   +1 more source

Pooling or sampling: Collective dynamics for electrical flow estimation [PDF]

, 2018
The computation of electrical flows is a crucial primitive for many recently proposed optimization algorithms on weighted networks. While typically implemented as a centralized subroutine, the ability to perform this task in a fully decentralized way is ...
Becchetti, Luca, Bonifaci, Vincenzo, Natale, Emanuele   +2 more
core  

Device‐Level Implementation of Reservoir Computing With Memristors

Advanced Intelligent Systems, EarlyView.
Reservoir computing (RC) is an emerging computing scheme that employs a reservoir and a single readout layer, which can be actualized in the nanoscale with memristors. As a comprehensive overview, the principles of RC and the switching mechanisms of memristors are discussed, followed by actual demonstrations of memristor‐based RC and the remaining ...
Sunbeom Park, Hyojung Kim, Ho Won Jang
wiley   +1 more source

The Argyris isogeometric space on unstructured multi-patch planar domains

, 2018
Multi-patch spline parametrizations are used in geometric design and isogeometric analysis to represent complex domains. We deal with a particular class of $C^0$ planar multi-patch spline parametrizations called analysis-suitable $G^1$ (AS-$G^{1}$) multi-
Kapl, Mario, Sangalli, Giancarlo, Takacs, Thomas   +2 more
core   +1 more source

QS4D: Quantization‐Aware Training for Efficient Hardware Deployment of Structured State‐Space Sequential Models

Advanced Intelligent Systems, EarlyView.
Quantization‐aware training creates resource‐efficient structured state space sequential S4(D) models for ultra‐long sequence processing in edge AI hardware. Including quantization during training leads to efficiency gains compared to pure post‐training quantization.
Sebastian Siegel, Ming‐Jay Yang, Younes Bouhadjar, Maxime Fabre, Emre Neftci, John Paul Strachan   +5 more
wiley   +1 more source

The type numbers of closed geodesics

, 2010
A short survey on the type numbers of closed geodesics, on applications of the Morse theory to proving the existence of closed geodesics and on the recent progress in applying variational methods to the periodic problem for Finsler and magnetic ...
A. Bahri, A. Borel, A. Nabutovsky, A.B. Katok, A.I. Fet, A.S. Schwarz, A.V. Pajitnov, D. Gromoll, D.V. Anosov, D.V. Anosov, D.V. Anosov, D.V. Anosov, G. Contreras, H. Seifert, H.-B. Rademacher, H.-B. Rademacher, H.-B. Rademacher, I. A. Taimanov, I.A. Taimanov, I.A. Taimanov, I.A. Taimanov, I.A. Taimanov, J. Franks, J. Milnor, L.A. Lusternik, L.A. Lusternik, L.S. Pontryagin, L.S. Pontryagin, M. Farber, M. Gromov, M. Morse, M. Vigué-Poirrier, N. Hingston, P.G. Grinevich, R. Bott, R. Bott, S.I. Al’ber, S.P. Novikov, S.P. Novikov, S.P. Novikov, S.P. Novikov, S.P. Novikov, V. aBngert, V. Bangert, V. Bangert, V. Bangert, V. Ginzburg, V.I. Arnold, V.L. Ginzburg, V.S. Guba, V.V. Kozlov, W. Ballmann, W. Ballmann, W. Ballmann, W. Ballmann, W. Ballmann, W. Klingenberg, W. Klingenberg, W. Klingenberg, W. Ziller, Y. Long, Y. Long, Y. Long   +62 more
core   +1 more source

A Flexible and Energy‐Efficient Compute‐in‐Memory Accelerator for Kolmogorov–Arnold Networks

Advanced Intelligent Systems, EarlyView.
This article presents KA‐CIM, a compute‐in‐memory accelerator for Kolmogorov–Arnold Networks (KANs). It enables flexible and efficient computation of arbitrary nonlinear functions through cross‐layer co‐optimization from algorithm to device. KA‐CIM surpasses CPU, ASIC, VMM‐CIM, and prior KAN accelerators by 1–3 orders of magnitude in energy‐delay ...
Chirag Sudarshan, Oliver Artner, Paul‐Philipp Manea, Sebastian Siegel, Susanne Hoffmann‐Eifert, Regina Dittmann, John Paul Strachan   +6 more
wiley   +1 more source

Activation‐Integrated and Memory‐Assisted Dynamic‐Latch Quantizer for Variation‐Tolerant and Low‐Energy Neuromorphic Computing

Advanced Intelligent Systems, EarlyView.
A memory‐assisted dynamic‐latch ADC integrating charge‐trap flash enables ultra‐low‐energy quantization and in‐ADC nonlinear activation for variation‐tolerant neuromorphic computing. Analog‐to‐digital converters (ADCs) remain the dominant area/energy bottleneck in neuromorphic computing (NC) systems.
Jonghyun Ko, Jiseong Im, Ryun‐Han Koo, Sung‐Ho Park, Jong‐Ho Lee   +4 more
wiley   +1 more source

A combinatorial Li-Yau inequality and rational points on curves

, 2015
We present a method to control gonality of nonarchimedean curves based on graph theory. Let k denote a complete nonarchimedean valued field.We first prove a lower bound for the gonality of a curve over the algebraic closure of k in terms of the minimal ...
Cornelissen, G., Kato, F., Kool, J.
core   +2 more sources

Experimental methods in chemical engineering: Atomic absorption spectrometry—AAS

The Canadian Journal of Chemical Engineering, EarlyView.
Abstract Elements absorb electromagnetic radiation (light) of a specific wavelength in proportion to the number of atoms in its path. As the atoms absorb this light energy, electrons rise from the ground state to an excited state. In atomic absorption spectrometry (AAS), high temperatures produce clouds of atoms from the sample (atomization) and ...
Emily Cintia Tossi de A. Costa, Jildimara de Jesus Santana, Viviane de Oliveira Campos, Felipe Fernandes Barbosa, Gregory S. Patience   +4 more
wiley   +1 more source