Training spiking neural networks using lessons from deep learning

JK Eshraghian, M Ward, EO Neftci… - Proceedings of the …, 2023 - ieeexplore.ieee.org
The brain is the perfect place to look for inspiration to develop more efficient neural
networks. The inner workings of our synapses and neurons provide a glimpse at what the …

[HTML][HTML] Modeling and simulating in-memory memristive deep learning systems: An overview of current efforts

C Lammie, W Xiang, MR Azghadi - Array, 2022 - Elsevier
Deep Learning (DL) systems have demonstrated unparalleled performance in many
challenging engineering applications. As the complexity of these systems inevitably …

MemTorch: An open-source simulation framework for memristive deep learning systems

C Lammie, W Xiang, B Linares-Barranco, MR Azghadi - Neurocomputing, 2022 - Elsevier
Memristive devices have shown great promise to facilitate the acceleration and improve the
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 …

Embedded intelligence: State-of-the-art and research challenges

KP Seng, LM Ang - IEEE Access, 2022 - ieeexplore.ieee.org
Recent years have seen deployments of increasingly complex artificial intelligent (AI) and
machine learning techniques being implemented on cloud server architectures and …

Gradient-based neuromorphic learning on dynamical RRAM arrays

P Zhou, DU Choi, WD Lu, SM Kang… - IEEE Journal on …, 2022 - ieeexplore.ieee.org
We present MEMprop, the adoption of gradient-based learning to train fully memristive
spiking neural networks (MSNNs). Our approach harnesses intrinsic device dynamics to …

Pinning synchronization of stochastic neutral memristive neural networks with reaction–diffusion terms

X Wu, S Liu, H Wang - Neural networks, 2023 - Elsevier
This paper investigates the pinning synchronization of stochastic neutral memristive neural
networks with reaction–diffusion terms. Firstly, two novel pinning controllers, which contain …

A monolithic stochastic computing architecture for energy efficient arithmetic

H Ravichandran, Y Zheng… - Advanced …, 2023 - Wiley Online Library
As the energy and hardware investments necessary for conventional high‐precision digital
computing continue to explode in the era of artificial intelligence (AI), a change in paradigm …

Low-variance memristor-based multi-level ternary combinational logic

XY Wang, CT Dong, PF Zhou, SK Nandi… - … on Circuits and …, 2022 - ieeexplore.ieee.org
This paper presents a series of multi-stage hybrid memristor-CMOS ternary combinational
logic stages that are optimized for reducing silicon area occupation. Prior demonstrations of …

Stability analysis of fractional reaction-diffusion memristor-based neural networks with neutral delays via Lyapunov functions

X Wu, S Liu, H Wang, J Sun, W Qiao - Neurocomputing, 2023 - Elsevier
In the realm of stability analysis for fractional neutral neural networks, it is not uncommon to
encounter erroneous Lyapunov functions. To investigate the stability of fractional memristor …