Results 61 to 70 of about 2,451 (213)
Neural network learning using non-ideal resistive memory devices
Frontiers in Nanotechnology, 2022 We demonstrate a modified stochastic gradient (Tiki-Taka v2 or TTv2) algorithm for deep learning network training in a cross-bar array architecture based on ReRAM cells.
Youngseok Kim +9 more
doaj +1 more source
Design and Evaluation of Monolithic Computers Implemented Using Crossbar ReRAM [PDF]
, 2019 A monolithic computer is an emerging architecture in which a multicore CPU and a high-capacity main memory system are all integrated in a single die. We believe such architectures will be possible in the near future due to nonvolatile memory technology ...
Singh, Devesh +8 more
core +1 more source
Emerging Memory and Device Technologies for Hardware‐Accelerated Model Training and Inference
Advanced Electronic Materials, EarlyView.This review investigates the suitability of various emerging memory technologies as compute‐in‐memory hardware for artificial intelligence (AI) applications. Distinct requirements for training‐ and inference‐centric computing are discussed, spanning device physics, materials, and system integration.
Yoonho Cho +6 more
wiley +1 more source
Analog Weight Update Rule in Ferroelectric Hafnia, Using picoJoule Programming Pulses
Advanced Electronic Materials, EarlyView.Resistive, ferroelectric synaptic weights based on BEOL‐compatible hafnia/zirconia nanolaminates are fabricated. Lateral downscaling the devices below 10 µm2 enables 20 ns programming with electrical pulses, dissipating ≤ 3 pJ. Experimental results show that final conductance state is set by pulse amplitude, and is largely independent of the initial ...
Alexandre Baigol +7 more
wiley +1 more source
ReGra: Accelerating Graph Traversal Applications Using ReRAM With Lower Communication Cost
IEEE Access, 2020 There is a growing gap between data explosion speed and the improvement of graph processing systems on conventional architectures. The main reason lies in the large overhead of random access and data movement, as well as the unbalanced and unordered ...
Haoqiang Liu +3 more
doaj +1 more source
High-Quality Single-Crystalline β-Ga2O3 Nanowires: Synthesis to Nonvolatile Memory Applications
Nanomaterials, 2021 One of the promising nonvolatile memories of the next generation is resistive random-access memory (ReRAM). It has vast benefits in comparison to other emerging nonvolatile memories.
Chandrasekar Sivakumar +5 more
doaj +1 more source
Advanced Electronic Materials, EarlyView.In this work, low‐resolution infrared imaging is combined with a 28 nm FeFET IMC architecture to enable compact, energy‐efficient edge inference. MLC FeFET devices are experimentally characterized, and controlled multi‐level current accumulation is validated at crossbar array level.
Alptekin Vardar +9 more
wiley +1 more source
An Energy-Efficient Digital ReRAM-Crossbar-Based CNN With Bitwise Parallelism
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 2017 There is great attention to develop hardware accelerator with better energy efficiency, as well as throughput, than GPUs for convolutional neural network (CNN). The existing solutions have relatively limited parallelism as well as large power consumption
Leibin Ni +3 more
doaj +1 more source
Frontiers in Electronic Materials, 2023 Memristive devices are the subject of extensive studies nowadays. While the Dynamic Route Map is a powerful tool for analyzing the response of first-order memristors under DC stimuli, the development of an equivalent tool for investigating the response ...
A. Ascoli +5 more
doaj +1 more source
Current Compliance-Dependent Nonlinearity in ${\rm TiO}_{2}$ ReRAM
, 2013 Nonvolatile redox-based resistive RAM (ReRAM) is considered to be a promising candidate for passive nanocrossbar integration. For this application, a high degree of nonlinearity in I-V characteristics of the ReRAM device is required.
Wouters, Dirk J. +5 more
core +1 more source