Article
Physics, Applied
Mohammad Javad Mirshojaeian Hosseini, Elisa Donati, Tomoyuki Yokota, Sunghoon Lee, Giacomo Indiveri, Takao Someya, Robert A. Nawrocki
Summary: Organic electronics have been used to implement an Integrate-and-Fire spiking neuron based on the Axon-Hillock CMOS circuit, demonstrating bio-compatibility and flexibility. This study showcases the operation characteristics and computing capabilities of the organic neuromorphic circuit, with low power dissipation.
JOURNAL OF PHYSICS D-APPLIED PHYSICS
(2021)
Article
Optics
Krzysztof Tyszka, Magdalena Furman, Rafal Mirek, Mateusz Krol, Andrzej Opala, Bartlomiej Seredynski, Jan Suffczynski, Wojciech Pacuski, Michal Matuszewski, Jacek Szczytko, Barbara Pietka
Summary: This paper introduces a new approach to neuromorphic photonics using microcavities as building blocks of optical spiking neurons, and demonstrates its feasibility through experimental results. The research shows that exciton-polaritons exhibit characteristics similar to the Leaky Integrate-and-Fire (LIF) mechanism, enabling ultrafast processing on sub-ns timescales.
LASER & PHOTONICS REVIEWS
(2023)
Article
Engineering, Electrical & Electronic
Jeeson Kim, Vladmir Kornijcuk, Changmin Ye, Doo Seok Jeong
Summary: This study presents a method to emulate a leaky integrate-and-fire (LIF) model in a hardware-efficient manner using a simplified spike-response model (SRM0) and the template-scaling-based exponential function approximation (TS-EFA). The implementation in FPGA of 512 neurons conforming to SRM0 showcases high precision, low latency, and efficient hardware usage.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2021)
Article
Neurosciences
Yi Chen, Hanwen Liu, Kexin Shi, Malu Zhang, Hong Qu
Summary: This study investigates the issue of information loss in current spiking neural networks in the time domain. The authors propose a model that combines spiking neural networks with working memory, which enhances the network's ability to obtain global information and reduces information redundancy between adjacent time steps. The experimental results demonstrate that the proposed model can better process spike train data and achieves state-of-the-art performance in short time steps.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Mathematics, Applied
Chang-Yuan Cheng, Shyan-Shiou Chen, Rui-Hua Chen
Summary: This study investigates the firing behavior of neurons and their interconnections through experiments and theoretical analysis. By examining both single-neuron and coupled neuron models, the impact of parameter ranges and delay times on neuronal firing behavior is analyzed. The research reveals the influence of delayed adaptation on membrane potential and provides new insights into the dynamics of coupled neuron systems.
DISCRETE AND CONTINUOUS DYNAMICAL SYSTEMS-SERIES B
(2021)
Article
Computer Science, Information Systems
Arati Kumari Shah, Eou-Sik Cho, Jisun Park, Hyungsoon Shin, Seongjae Cho
Summary: In this study, a compact CMOS integrate-and-fire (I&F) neuron circuit with an operational transconductance amplifier (OTA) is designed. The OTA block ensures stability in I&F functions even at high-frequency operation. The designed circuit allows control of firing frequency by adjusting the synaptic pulse, resulting in high fidelity. Circuit simulations validate the functionality, and temperature dependence is investigated for robustness.
Article
Computer Science, Artificial Intelligence
Yongcheng Zhou, Anguo Zhang
Summary: The study shows that using the SynSup and SynAcc mechanisms can effectively improve the inference speed of spiking neural networks compared to the general I&F model.
APPLIED INTELLIGENCE
(2021)
Article
Engineering, Electrical & Electronic
Ashvinikumar Dongre, Gaurav Trivedi
Summary: This article introduces a self-resetting Integrate and Fire (I&F) neuron circuit based on Resistive Random Access Memory (RRAM). The circuit does not require any external bias voltage, and the integration of control unit into the neuron circuit optimizes its overall power consumption. The circuit consists of two RRAMs for integrate and fire operations, and a pulse propagation and reset circuit with 22 CMOS transistors. It consumes 1.5 fJ per spike, which is 48% and 53% less than recent neurons designed using nanoscale FBFET and PDSOI-MOSFET, respectively. The proposed neuron operates at frequencies ranging from 277 KHz to 03 MHz, at least 7.5% and 10% higher than the operating frequencies of the mentioned recent neurons, respectively. The inclusion of a reset circuit enables the implementation of large scale spiking neural networks (SNN), making it superior in terms of power and energy consumption.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Engineering, Electrical & Electronic
Avinash Lahgere
Summary: In this article, a trench Bipolar I-MOS is used for the realization of a spiking neural network by using calibrated 2-D TCAD simulations. The proposed trench Bipolar I-MOS LIF neuron can emulate the biological neuronal nature and has a low threshold voltage (-0.16 V) lower than the past reported LBIMOS LIF neuron. The trench Bipolar I-MOS neuron consumes 0.35 pJ energy per spike, which is much lower compared to other types of LIF neurons.
IEEE TRANSACTIONS ON NANOTECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Linjing Wang, Tianlan Mo, Xuetao Wang, Wentao Chen, Qiang He, Xin Li, Shuxu Zhang, Ruimeng Yang, Jialiang Wu, Xuejun Gu, Jun Wei, Peiliang Xie, Linghong Zhou, Xin Zhen
Summary: This study introduced a two-level framework, HF2HM, to integrate diversified classification models by feeding heterogeneous classifiers with homogeneous random-projected training datasets. Results showed the superiority of the proposed HF2HM framework over base classifiers and state-of-the-art benchmark ensemble methods, indicating its potential as a tool for medical decision making in practical clinical settings.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Verena Brehm, Johannes W. Austefjord, Serban Lepadatu, Alireza Qaiumzadeh
Summary: The proposed neuromorphic computing model based on antiferromagnetic domain walls can mimic the behavior of biological neurons and has faster processing speed and more functionalities compared to previous models based on ferromagnetic systems.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Electrical & Electronic
Mudasir A. Khanday, Farooq A. Khanday, Faisal Bashir, Furqan Zahoor
Summary: A single transistor leaky integrate-and-fire neuron based on the band to band tunneling mechanism is proposed, which achieves significant improvement in energy consumption and integration density. The device exploits the forward transfer characteristics of Tunnel FET to accurately emulate the spiking behavior of a biological neuron. Through calibrated simulation, it is demonstrated that the proposed LIF neuron consumes significantly less energy (750 fJ/spike) compared to previous 1-T neurons. The neuron is also used to implement reconfigurable threshold logic gates and demonstrates high accuracy (96.27%) in image recognition tasks, showcasing its potential for future neuromorphic computing.
IEEE TRANSACTIONS ON NANOTECHNOLOGY
(2023)
Article
Neurosciences
Larry Shupe, Eberhard Fetz
Summary: The study introduces an integrate-and-fire (IF) spiking neural network incorporating spike-timing-dependent plasticity (STDP) to simulate the outcomes of cortical plasticity produced by different conditioning protocols. The successful simulations demonstrate that closed-loop stimulation can mediate targeted plasticity. Additionally, the model allows computation of underlying network behavior and predictions for future experiments.
Article
Neurosciences
Youngeun Kim, Yuhang Li, Abhishek Moitra, Ruokai Yin, Priyadarshini Panda
Summary: Spiking Neural Networks (SNNs) are energy efficient neural networks that have gained attention for their binary and asynchronous computation. However, the non-linear activation of LIF neurons in SNNs requires additional memory. This study proposes EfficientLIF-Net, a solution that shares LIF neurons across different layers and channels, achieving comparable accuracy while improving memory efficiency for LIF neurons.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Neurosciences
Sijia Lu, Feng Xu
Summary: This paper establishes a precise mathematical mapping between the biological parameters of the LIF/SNNs and the parameters of ReLU-AN/DNNs, which is validated through simulation and experiments.
FRONTIERS IN NEUROSCIENCE
(2022)