Computer ScienceNature Communications
High-performance deep spiking neural networks with 0.3 spikes per neuron
A. Stanojevic, S. Woźniak, et al.
This innovative research, conducted by Ana Stanojevic and her team, delves into the training of time-to-first-spike networks, tackling the challenges inherent in biologically-inspired spiking neural networks. The findings unveil a specific parameterization that enables SNNs to achieve performance on par with traditional neural networks while utilizing fewer spikes per neuron.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Engineering and Technology
Enhanced detection of threat materials by dark-field x-ray imaging combined with deep neural networks
T. Partridge, A. Astolfo, et al.
Computer Science
Detection of eye contact with deep neural networks is as accurate as human experts
E. Chong, E. Clark-whitney, et al.
Computer Science
Multi-compartment Neuron and Population Encoding improved Spiking Neural Network for Deep Distributional Reinforcement Learning
Y. Sun, Y. Zeng, et al.
Humanities
Restoring and attributing ancient texts using deep neural networks
Y. Assael, T. Sommerschield, et al.
