Hardware implementation of memristor-based artificial neural networks
Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL)
techniques, which rely on networks of connected simple computing units operating in …
techniques, which rely on networks of connected simple computing units operating in …
Memristor-based binarized spiking neural networks: Challenges and applications
Memristive arrays are a natural fit to implement spiking neural network (SNN) acceleration.
Representing information as digital spiking events can improve noise margins and tolerance …
Representing information as digital spiking events can improve noise margins and tolerance …
Hardware implementation of deep network accelerators towards healthcare and biomedical applications
The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors
has brought on new opportunities for applying both Deep and Spiking Neural Network …
has brought on new opportunities for applying both Deep and Spiking Neural Network …
A 7-nm compute-in-memory SRAM macro supporting multi-bit input, weight and output and achieving 351 TOPS/W and 372.4 GOPS
In this work, we present a compute-in-memory (CIM) macro built around a standard two-port
compiler macro using foundry 8T bit-cell in 7-nm FinFET technology. The proposed design …
compiler macro using foundry 8T bit-cell in 7-nm FinFET technology. The proposed design …
Resistive crossbars as approximate hardware building blocks for machine learning: Opportunities and challenges
Traditional computing systems based on the von Neumann architecture are fundamentally
bottlenecked by data transfers between processors and memory. The emergence of data …
bottlenecked by data transfers between processors and memory. The emergence of data …
Multi-level, forming and filament free, bulk switching trilayer RRAM for neuromorphic computing at the edge
CMOS-RRAM integration holds great promise for low energy and high throughput
neuromorphic computing. However, most RRAM technologies relying on filamentary …
neuromorphic computing. However, most RRAM technologies relying on filamentary …
In-memory computing with resistive memory circuits: Status and outlook
G Pedretti, D Ielmini - Electronics, 2021 - mdpi.com
In-memory computing (IMC) refers to non-von Neumann architectures where data are
processed in situ within the memory by taking advantage of physical laws. Among the …
processed in situ within the memory by taking advantage of physical laws. Among the …
MemTorch: An open-source simulation framework for memristive deep learning systems
Memristive devices have shown great promise to facilitate the acceleration and improve the
power efficiency of Deep Learning (DL) systems. Crossbar architectures constructed using …
power efficiency of Deep Learning (DL) systems. Crossbar architectures constructed using …
How to build a memristive integrate-and-fire model for spiking neuronal signal generation
SM Kang, D Choi, JK Eshraghian… - … on Circuits and …, 2021 - ieeexplore.ieee.org
We present and experimentally validate two minimal compact memristive models for spiking
neuronal signal generation using commercially available low-cost components. The first …
neuronal signal generation using commercially available low-cost components. The first …
A multi-functional memristive Pavlov associative memory circuit based on neural mechanisms
Pavlov conditioning is a typical associative memory, which involves associative learning
between the gustatory and auditory cortex, known as Pavlov associative memory. Inspired …
between the gustatory and auditory cortex, known as Pavlov associative memory. Inspired …