Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
In this study, we analyzed the memristor device typically used as a synapse in neuromorphic architecture and confirmed that the synaptic memristor device can be adopted to perform the machine learning algorithm. The nonlinear characteristics of the memristor complicates its use as the neuromorphic hardware in an artificial neural network (ANN) with a back-propagation algorithm. Using a memristor device with a nonlinear characteristic, we demonstrated that pattern classification can be implemented in ANNs using the Guide training algorithm without back-propagation. Furthermore, the memristor characteristics required to achieve accurate learning results are analyzed.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1166/jnn.2019.17110 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Bioinspired neuromorphic memristor with logical operation for precision sperm detection in seminiferous tubules.
Mater Today Bio
October 2025
Department of Reproductive Medicine, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi, 710061, China.
Clinically, even in patients diagnosed with non-obstructive azoospermia, spermatogenesis may be present in some seminiferous tubules, which gives the patient hope of having biological offspring of his own. However, there is still a blank for high-precision detection technologies to support accurate diagnosis and effective treatment. In this work, we successfully developed a minimally invasive fine needle detection memristive device that features a structure composed of Ag/CH-MnO/FTO by utilizes the organic-inorganic heterojunction as functional layer.
View Article and Find Full Text PDFA ferroelectrics/oxide heterojunction based memristor for artificial synapse and neuromorphic computing.
J Colloid Interface Sci
September 2025
School of Electronic Information & Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an 710021, China.
The integration of information memory and computing enabled by nonvolatile memristive device has been widely acknowledged as a critical solution to circumvent the von Neumann architecture limitations. Herein, the Au/NiO/CaBiTiO/FTO (CBTi/NiO) heterojunction based memristor with varying film thicknesses are demonstrated on FTO/glass substrates, and the CBTi/NiO-4 sample shows the optimal memristor characteristics with 5 × 10 stable switching cycles and 10-s resistance state retention. The electrical conduction in the low-resistance state is dominated by Ohmic behavior, while the high-resistance state exhibited characteristics consistent with the space-charge-limited conduction (SCLC) model.
View Article and Find Full Text PDFEffects of non-volatility of memristor on the synchronizability of memristor-coupled heterogeneous neurons.
Chaos
September 2025
School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China.
Synaptic plasticity is of great significance for understanding the leaning and memory processes in different brain regions since it determines the synchronized firing activities of neurons. A volatility-switchable memristor-coupled heterogeneous neuron model is proposed to explore the effects of the synaptic plasticity on the synchronous dynamics of coupled neurons in different brain regions. With the increment of the non-volatility, the critical coupling strength of synchronization between two heterogeneous neurons decreases in a power-law relationship with the character parameter of the memristor.
View Article and Find Full Text PDF2D Tellurene-Based Optoelectronic Memristor with Temporal Dynamics for Multimodal Reservoir Computing System.
Adv Sci (Weinh)
September 2025
State Key Laboratory of Integrated Optoelectronics, Key Laboratory of UV Light-Emitting Materials and Technology of Ministry of Education, Northeast Normal University, Changchun, Jilin, 130024, China.
Neuromorphic multimodal perception of sensory systems can integrate the stimulation from different senses, thus enhancing the perception accuracy of organisms to understand the external environment. An optoelectronic memristor with the capability to combine multidimensional sensing and processing functions is highly desirable for developing efficient neuromorphic multimodal sensory systems (MSSs). In this work, a tellurene (Te) nanoflake-based optoelectronic memristor relying on solution plasma process (SPP) treatment is demonstrated for the first time, which is capable of combining infrared (IR) optical and electrical stimuli in a single synaptic device for a multisensory integration function.
View Article and Find Full Text PDFInSe Dynamic Memristor-Based Reservoir Computing for Temporal and Spatial Signal Recognition.
Nano Lett
September 2025
Institute of Marine Science and Technology, Shandong University, Qingdao, Shandong 266237, China.
Multimodal recognition techniques are pivotal for advancing contemporary artificial intelligence, particularly in enhancing visual perception. However, research on electronic devices capable of robust multimodal recognition remains limited. In this study, we employ an InSe/AlO/ Pb(Zr·Ti·)O (PZT) heterostructure as a dynamic memristor.
View Article and Find Full Text PDF