paper-with-me

Papers

Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

2021-03-12 · Bojian Yin, Federico Corradi, Sander M. Bohte

Inspired by more detailed modeling of biological neurons, Spiking neural networks (SNNs) have been investigated both as more biologically plausible and potentially more powerful models of neural computation, and also with the aim of extracting biological neurons' energy efficiency; the performance of such networks however has remained lacking compared to classical artificial neural networks (ANNs). Here, we demonstrate how a novel surrogate gradient combined with recurrent networks of tunable and adaptive spiking neurons yields state-of-the-art for SNNs on challenging benchmarks in the time-domain, like speech and gesture recognition. This also exceeds the performance of standard classical recurrent neural networks (RNNs) and approaches that of the best modern ANNs. As these SNNs exhibit sparse spiking, we show that they theoretically are one to three orders of magnitude more computationally efficient compared to RNNs with comparable performance. Together, this positions SNNs as an attractive solution for AI hardware implementations.

📄 PDF Abstract BibTeX arXiv:2103.12593

Code (0)

등록된 구현이 없습니다.

Tasks

Audio Classificationdomain classificationGeneral ClassificationGesture Recognition

Similar Papers 제목 키워드 기반

Accurate Mapping of RNNs on Neuromorphic Hardware with Adaptive Spiking Neurons

2024-07-18 · Gauthier Boeshertz, Giacomo Indiveri, Manu Nair, Alpha Renner

Thanks to their parallel and sparse activity features, recurrent neural networks (RNNs) are well-suited for hardware implementation in low-power neuromorphic hardware. However, mapping rate-based RNNs to hardware-compati…

Edge-computing

Efficient Converted Spiking Neural Network for 3D and 2D Classification

2023-01-01 · ICCV 2023 1 · Yuxiang Lan, Yachao Zhang, Xu Ma, Yanyun Qu 외

Spiking Neural Networks (SNNs) have attracted enormous research interest due to their low-power and biologically plausible nature. Existing ANN-SNN conversion methods can achieve lossless conversion by converting a w…

image-classificationImage ClassificationPoint Cloud Classification

Spiking Neural Networks for Mental Workload Classification with a Multimodal Approach

2025-09-17 · Jiahui An, Sara Irina Fabrikant, Giacomo Indiveri, Elisa Donati arxiv

Accurately assessing mental workload is crucial in cognitive neuroscience, human-computer interaction, and real-time monitoring, as cognitive load fluctuations affect performance and decision-making. While Electroencepha…

When Spiking neural networks meet temporal attention image decoding and adaptive spiking neuron

2024-06-05 · Xuerui Qiu, Zheng Luan, Zhaorui Wang, Rui-Jie Zhu

Spiking Neural Networks (SNNs) are capable of encoding and processing temporal information in a biologically plausible way. However, most existing SNN-based methods for image tasks do not fully exploit this feature. More…

On robot compliance. A cerebellar control approach

2020-03-02 · Ignacio Abadia, Francisco Naveros, Jesus A. Garrido, Eduardo Ros 외

The work presented here is a novel biological approach for the compliant control of a robotic arm in real time (RT). We integrate a spiking cerebellar network at the core of a feedback control loop performing torque-driv…