4.6 Article

Experimental Analysis of Oxide-Based RAM Analog Synaptic Behavior

Related references

Note: Only part of the references are listed.
Article Computer Science, Hardware & Architecture

RRAM-based non-volatile SRAM cell architectures for ultra-low-power applications

Hussein Bazzi et al.

Summary: This paper introduces the concept of Non-Volatile SRAM (NVSRAM) and explores their principle of operation under different structures, while comparing the performance metrics of three NVSRAM memory cells implemented in a 130-nm high voltage CMOS technology from STMicroelectronics.

ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING (2021)

Article Automation & Control Systems

Memristive Quantized Neural Networks: A Novel Approach to Accelerate Deep Learning On-Chip

Yang Zhang et al.

Summary: This paper presents a novel approach to accelerate on-chip learning systems using memristive quantized neural networks (M-QNNs) to address the computational and memory challenges of existing deep neural networks. The method involves adding different levels of Gaussian noise to the memristive model to tackle multilevel variations in synaptic weights and utilizes memristors with binary states to build M-QNNs, which reduces D2D and C2C variations. Additionally, solutions for sneak path issues in memristive crossbar arrays are proposed, while the proposed method significantly reduces computational time and memory during image recognition.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Density Enhancement of RRAMs using a RESET Write Termination for MLC Operation

H. Aziza et al.

Summary: A novel design scheme proposed in this paper achieves reliable and uniform MLC RRAM operation without the need of read verification. The MLC is implemented based on a strict control of the cell programming currents of 1T-1R HfO2-based RRAM cells.

PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021) (2021)

Article Engineering, Electrical & Electronic

Compute-in-Memory Chips for Deep Learning: Recent Trends and Prospects

Shimeng Yu et al.

Summary: Compute-in-memory (CIM) is a new computing paradigm that addresses the memory-wall problem by performing multiply-and-accumulate (MAC) operations in the analog domain within memory sub-array, leading to significant improvements in throughput and energy efficiency for deep learning. SRAM and RRAM are promising candidates to store the weights of deep neural network (DNN) models.

IEEE CIRCUITS AND SYSTEMS MAGAZINE (2021)

Article Computer Science, Hardware & Architecture

Improving TID Radiation Robustness of a CMOS OxRAM-Based Neuron Circuit by Using Enclosed Layout Transistors

Pablo Ilha Vaz et al.

Summary: In aerospace applications, improving the radiation hardening characteristics of neural circuits can be achieved by changing the MOS gate geometry and utilizing radiation-tolerant OxRAM, along with hardened devices such as ELTs. By introducing an enclosed gate geometry to the conventional circuit layout and utilizing OxRAM as a memory element, the proposed hardened neuron circuit presents a feasible solution for embedding neuromorphic computing in aerospace applications.

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS (2021)

Article Computer Science, Information Systems

An Energy-Efficient Current-Controlled Write and Read Scheme for Resistive RAMs (RRAMs)

H. Aziza et al.

IEEE ACCESS (2020)

Article Engineering, Electrical & Electronic

True Random Number Generator Integration in a Resistive RAM Memory Array Using Input Current Limitation

Hassen Aziza et al.

IEEE TRANSACTIONS ON NANOTECHNOLOGY (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Neural Networks at the Edge

Deboleena Roy et al.

2019 IEEE INTERNATIONAL CONFERENCE ON SMART COMPUTING (SMARTCOMP 2019) (2019)

Article Engineering, Electrical & Electronic

Resistive RAMs as analog trimming elements

H. Aziza et al.

SOLID-STATE ELECTRONICS (2018)

Article Engineering, Electrical & Electronic

Design and Simulation of a 128 kb Embedded Nonvolatile Memory Based on a Hybrid RRAM (HfO2)/28 nm FDSOI CMOS Technology

Jean-Michel Portal et al.

IEEE TRANSACTIONS ON NANOTECHNOLOGY (2017)

Article Multidisciplinary Sciences

Face classification using electronic synapses

Peng Yao et al.

NATURE COMMUNICATIONS (2017)

Article Engineering, Electrical & Electronic

3-Bit Multilevel Switching by Deep Reset Phenomenon in Pt/W/TaOX/Pt-ReRAM Devices

W. Kim et al.

IEEE ELECTRON DEVICE LETTERS (2016)

Review Engineering, Electrical & Electronic

Resistive switching memories based on metal oxides: mechanisms, reliability and scaling

Daniele Ielmini

SEMICONDUCTOR SCIENCE AND TECHNOLOGY (2016)

Article Engineering, Electrical & Electronic

HfO2-Based OxRAM Devices as Synapses for Convolutional Neural Networks

Daniele Garbin et al.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2015)

Article Engineering, Electrical & Electronic

Switching characteristics of W/Zr/HfO2/TiN ReRAM devices for multi-level cell non-volatile memory applications

Wenbo Chen et al.

SEMICONDUCTOR SCIENCE AND TECHNOLOGY (2015)

Article Engineering, Electrical & Electronic

Multilevel Switching in Forming-Free Resistive Memory Devices With Atomic Layer Deposited HfTiOx Nanolaminate

Bhaswar Chakrabarti et al.

IEEE ELECTRON DEVICE LETTERS (2013)

Article Neurosciences

Stochastic learning in oxide binary synaptic device for neuromorphic computing

Shimeng Yu et al.

FRONTIERS IN NEUROSCIENCE (2013)

Article Nanoscience & Nanotechnology

Beyond von Neumann-logic operations in passive crossbar arrays alongside memory operations

E. Linn et al.

NANOTECHNOLOGY (2012)

Review Neurosciences

Neuromorphic silicon neuron circuits

Giacomo Indiveri et al.

FRONTIERS IN NEUROSCIENCE (2011)