Artificial neural networks (ANNs) based on synaptic devices, which can simultaneously perform processing and storage of data, have superior computing performance compared to conventional von Neumann architectures. Here, we present a ferroelectric coupled artificial synaptic device with reliable weight update and storage properties for ANNs. The artificial synaptic device, which is based on a ferroelectric polymer capacitively coupled with an oxide dielectric via an electric-field-permeable, semiconducting single-walled carbon-nanotube channel, is successfully fabricated by inkjet printing. By controlling the ferroelectric polarization, synaptic dynamics, such as excitatory and inhibitory postsynaptic currents and long-term potentiation/depression characteristics, is successfully implemented in the artificial synaptic device. Furthermore, the constructed ANN, which is designed in consideration of the device-to-device variation within the synaptic array, efficiently executes the tasks of learning and recognition of the Modified National Institute of Standards and Technology numerical patterns.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1021/acsami.9b17742 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A robust Parkinson's disease detection model based on time-varying synaptic efficacy function in spiking neural network.
BMC Neurol
December 2024
Department of Environmental Health, Harvard T H Chan School of Public Health, Boston, MA, 02115, USA.
Parkinson's disease (PD) is a neurodegenerative disease affecting millions of people around the world. Conventional PD detection algorithms are generally based on first and second-generation artificial neural network (ANN) models which consume high energy and have complex architecture. Considering these limitations, a time-varying synaptic efficacy function based leaky-integrate and fire neuron model, called SEFRON is used for the detection of PD.
View Article and Find Full Text PDFSolid-State Oxide-Ion Synaptic Transistor for Neuromorphic Computing.
Adv Mater
December 2024
Catalonia Institute for Energy Research (IREC), Jardins de les Dones de Negre 1, 2, Sant Adriá de Besós, Barcelona, 08930, Spain.
Neuromorphic hardware facilitates rapid and energy-efficient training and operation of neural network models for artificial intelligence. However, existing analog in-memory computing devices, like memristors, continue to face significant challenges that impede their commercialization. These challenges include high variability due to their stochastic nature.
View Article and Find Full Text PDFExploring the Conductive Dynamics of Sb(S,Se)-Based Memristors for Non-Volatile Memory and Neuromorphic Applications.
J Phys Chem Lett
December 2024
School of Integrated Circuit Science and Engineering, Tianjin Key Laboratory of Film Electronic and Communication Devices, Tianjin University of Technology, Tianjin 300384, China.
Advancing the development of novel materials or architectures for random access memories, coupled with an in-depth understanding of their intrinsic conduction mechanisms, holds the potential to transcend the conventional von Neumann bottleneck. In this work, a novel memristor based on the Sb(S,Se) material with an alloy of S and Se was fabricated. A systematic investigation of the correlation between the Se/(S + Se) ratio and memristive performance revealed that Ag/Sb(S,Se)/FTO memristive behavior is uniquely associated with the formation and disruption of anion vacancies and silver filaments.
View Article and Find Full Text PDFA recurrent neural circuit in Drosophila temporally sharpens visual inputs.
Curr Biol
December 2024
Department of Neurobiology, Stanford University, Stanford, CA 94305, USA. Electronic address:
A critical goal of vision is to detect changes in light intensity, even when these changes are blurred by the spatial resolution of the eye and the motion of the animal. Here, we describe a recurrent neural circuit in Drosophila that compensates for blur and thereby selectively enhances the perceived contrast of moving edges. Using in vivo, two-photon voltage imaging, we measured the temporal response properties of L1 and L2, two cell types that receive direct synaptic input from photoreceptors.
View Article and Find Full Text PDFThe discharge characteristics of motor units innervating functionally paralyzed muscles.
J Neurophysiol
December 2024
Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91052 Erlangen, Germany.
For individuals with motor complete spinal cord injury (SCI), previous works have shown that spared motor neurons below the injury level can still be voluntarily controlled. In this study, we investigated the behavior of these neurons after SCI by analyzing neural and spatial properties of individual motor units using high-density surface electromyography (HDsEMG) and ultrasound imaging. The dataset for this study is based on motor unit data from our previous work (Oliveira .
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!