Cargando…
Neural Network Training Acceleration With RRAM-Based Hybrid Synapses
Hardware neural network (HNN) based on analog synapse array excels in accelerating parallel computations. To implement an energy-efficient HNN with high accuracy, high-precision synaptic devices and fully-parallel array operations are essential. However, existing resistive memory (RRAM) devices can...
Autores principales: | Choi, Wooseok, Kwak, Myonghoon, Kim, Seyoung, Hwang, Hyunsang |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8264206/ https://www.ncbi.nlm.nih.gov/pubmed/34248492 http://dx.doi.org/10.3389/fnins.2021.690418 |
Ejemplares similares
-
Linear Frequency Modulation of NbO(2)-Based Nanoscale Oscillator With Li-Based Electrochemical Random Access Memory for Compact Coupled Oscillatory Neural Network
por: Lee, Donguk, et al.
Publicado: (2022) -
Weighted Synapses Without Carry Operations for RRAM-Based Neuromorphic Systems
por: Liao, Yan, et al.
Publicado: (2018) -
Graphene-based RRAM devices for neural computing
por: R, Rajalekshmi T., et al.
Publicado: (2023) -
Near ideal synaptic functionalities in Li ion synaptic transistor using Li(3)PO(x)Se(x) electrolyte with high ionic conductivity
por: Nikam, Revannath Dnyandeo, et al.
Publicado: (2019) -
Simulation of Inference Accuracy Using Realistic RRAM Devices
por: Mehonic, Adnan, et al.
Publicado: (2019)