Article
Telecommunications
Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
Summary: This paper introduces the operation principle, training algorithms, and models of Spiking Neural Networks (SNNs) and compares two main methods. To address the non-differentiability of the spiking mechanism, a differentiable function approximating the threshold activation function is proposed, and an alternative method based on probability models is discussed. Finally, experimental results on accuracy and convergence under different SNN models are provided.
IEEE COMMUNICATIONS LETTERS
(2021)
Article
Telecommunications
Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
Summary: The synergies between wireless communications and artificial intelligence are increasingly driving research at the intersection of the two fields. Machine learning can address algorithm and model deficits in the optimization of communication protocols, but implementing ML models on devices connected via bandwidth-constrained channels remains challenging.
IEEE COMMUNICATIONS LETTERS
(2021)
Article
Computer Science, Hardware & Architecture
Jianwei Xue, Rendong Ying, Faquan Chen, Peilin Liu
Summary: This work presents SFANC, a scalable and flexible neuromorphic architecture for spiking neural networks (SNNs) based on optimized router architecture and programmable neuromorphic cores (NCs). SFANC exhibits high performance, flexibility, and scalability through its optimized design, SNN-specific instructions, and spectral cluster mapping approach.
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Congyang Liu, Ziyi Yang, Xin Zhang, Zikai Zhu, Haoming Chu, Yuxiang Huan, Li-Rong Zheng, Zhuo Zou
Summary: In this work, a neuromorphic processor is presented for AIoT applications, featuring low-power consumption, small footprint, STDP-based online learning, and the ability to adapt to multiple applications. The use of hybrid precision, precision-configurable neuron units, unified memory architecture, and dynamic pruning technique contributes to improved energy and time efficiency in training and inference.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Computer Science, Artificial Intelligence
Manon Dampfhoffer, Thomas Mesquida, Alexandre Valentian, Lorena Anghel
Summary: With the widespread use of smart systems, artificial neural networks (ANNs) have been widely adopted. However, the high energy consumption of traditional ANN implementations limits their applications in embedded and mobile systems. Spiking neural networks (SNNs) are gaining interest as low-power alternatives to ANNs due to their ability to mimic the dynamics of biological neural networks. However, training SNNs using backpropagation-based techniques is challenging due to the discrete representation of information.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Chemistry, Physical
Dongyeol Ju, Minsuk Koo, Sungjun Kim, Toma Stoica
Summary: This paper investigates the bipolar resistive switching and synaptic characteristics of IZO single-layer and IZO/SiO2 bilayer two-terminal memory devices. The results show that the device with the SiO2 layer has a lower current level and better uniformity, and exhibits favorable abilities in neuromorphic applications.
Article
Neurosciences
Tian Gao, Bin Deng, Jiang Wang, Guosheng Yi
Summary: This paper investigates the efficient architecture of spiking neural network (SNN) on FPGA to reduce resource and power consumption. By using the multi-compartment leaky integrate-and-fire (MLIF) model and shift multiplier, piecewise linear algorithm, a neuromorphic learning system with high resource utilization and power efficiency is achieved.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Engineering, Electrical & Electronic
Jason K. Eshraghian, Max Ward, Emre O. Neftci, Xinxin Wang, Gregor Lenz, Girish Dwivedi, Mohammed Bennamoun, Doo Seok Jeong, Wei D. Lu
Summary: This article discusses how to apply decades of research in deep learning, gradient descent, backpropagation, and neuroscience to biologically plausible spiking neural networks (SNNs) and how deep learning can move towards biologically plausible online learning. The article also explores the interplay between encoding data as spikes and the learning process, the challenges and solutions of applying gradient-based learning to SNNs, the subtle link between temporal backpropagation and spike timing-dependent plasticity. Some ideas are well accepted and commonly used among the neuromorphic engineering community, while others are presented or justified for the first time here.
PROCEEDINGS OF THE IEEE
(2023)
Article
Computer Science, Artificial Intelligence
Fernando M. Quintana, Fernando Perez-Pena, Pedro L. Galindo
Summary: This paper presents a learning method called Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) that modulates the synaptic plasticity in a Spiking Neural Network (SNN) using an external learning signal. By combining the advantages of reinforcement learning and the biological plausibility of STDP, online learning on SNN in real-world scenarios is enabled. The hardware implementation on an FPGA demonstrates comparable results to software simulations and achieves high accuracy and resource efficiency in an obstacle avoidance problem on mobile robotics.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Antonio Vitale, Elisa Donati, Roger Germann, Michele Magno
Summary: With the emergence of edge-computing platforms, the applications of smart wearable devices are immense. This article presents two spiking neural networks (SNNs) for event-based electromyography (EMG) gesture recognition and their evaluation on Intel's research neuromorphic chip Loihi. The proposed method achieves a high accuracy of 74% on the commonly used NinaPro DB5 dataset and a low processing latency of 5.7 ms for 300-ms EMG samples while consuming only 41 mW.
IEEE SENSORS JOURNAL
(2022)
Article
Chemistry, Multidisciplinary
Yue Wang, Kun Wang, Xiangyu Hu, Ya'kun Wang, Wandong Gao, Yiqiang Zhang, Zhenghui Liu, Yi Zheng, Ke Xu, Deren Yang, Xiaodong Pi
Summary: This study demonstrates the simultaneous modulation and visualization of synaptic events using optically stimulated synaptic devices based on the hetero-structure of fluorescent silicon quantum dots and monolayer molybdenum disulfide. These devices can mimic neural population coding and identify defective devices through the absence of fluorescence. This research has important implications for the development of synaptic devices.
Article
Chemistry, Physical
Junyao Zhang, Tianli Sun, Sheng Zeng, Dandan Hao, Ben Yang, Shilei Dai, Dapeng Liu, Lize Xiong, Cairong Zhao, Jia Huang
Summary: A multi-functional and energy-efficient optoelectronic synaptic transistor has been designed to achieve the required synaptic plasticity with both photonic and electric modulation modes in one device.
Article
Computer Science, Theory & Methods
Twisha Titirsha, Shihao Song, Anup Das, Jeffrey Krichmar, Nikil Dutt, Nagarajan Kandasamy, Francky Catthoor
Summary: This study addresses the issue of current asymmetry in memristive crossbars in neuromorphic computing systems and proposes a novel technique called eSpine to improve the lifetime of crossbars by considering the endurance variation of each memristor. The technique optimizes the mapping of machine learning workloads to ensure that synapses with higher activation are implemented on memristors with higher endurance.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Sarah A. El-Sayed, Theofilos Spyrou, Luis A. Camunas-Mesa, Haralampos-G Stratigopoulos
Summary: This paper addresses the issue of testing AI hardware accelerators that implement SNNs. The authors propose a metric to rank training and testing samples based on their fault detection capability, measuring the interclass spike count difference. They show that samples with low scores achieve high fault coverage and demonstrate that retaining a set of high-ranked samples results in near-perfect fault coverage for critical faults. The proposed approach is tested on Python models and actual neuromorphic hardware, and fault modeling is discussed to reduce test generation time.
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jangsaeng Kim, Dongseok Kwon, Sung Yun Woo, Won-Mook Kang, Soochang Lee, Seongbin Oh, Chul-Heung Kim, Jong-Ho Bae, Byung-Gook Park, Jong-Ho Lee
Summary: The study proposes a supervised on-chip training method for hardware-based SNNs, achieving high performance through the use of pulse schemes and bias synapse. Experimental results show that the system achieves a recognition rate similar to that of software-based networks in MNIST dataset classification.