Results 11 to 20 of about 22,581 (258)
Integrating Non-spiking Interneurons in Spiking Neural Networks [PDF]
Frontiers in Neuroscience, 2021 Researchers working with neural networks have historically focused on either non-spiking neurons tractable for running on computers or more biologically plausible spiking neurons typically requiring special hardware.
Beck Strohmer +3 more
doaj +5 more sources
Spiking neural networks for nonlinear regression [PDF]
Royal Society Open Science, 2023 Spiking neural networks (SNN), also often referred to as the third generation of neural networks, carry the potential for a massive reduction in memory and energy consumption over traditional, second-generation neural networks. Inspired by the undisputed
Alexander Henkes +2 more
doaj +6 more sources
Quantization in Spiking Neural Networks
CoRR, 2023 arXiv admin note: text overlap with arXiv:2305 ...
Bernhard Alois Moser, Michael Lunglmayr
openaire +2 more sources
Expressivity of Spiking Neural Networks
CoRR, 2023 The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications. Inspired by this potential, we revisit the foundational aspects to study the capabilities of spiking neural networks where information is encoded in the firing time of neurons.
Manjot Singh +2 more
openaire +2 more sources
Attention Spiking Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 18 pages, 8 figures, Under ...
Man Yao +7 more
openaire +3 more sources
Stochasticity and robustness in spiking neural networks [PDF]
Neurocomputing, 2021 Artificial neural networks normally require precise weights to operate, despite their origins in biological systems, which can be highly variable and noisy. When implementing artificial networks which utilize analog 'synaptic' devices to encode weights, however, inherent limits are placed on the accuracy and precision with which these values can be ...
Wilkie Olin-Ammentorp +4 more
openaire +2 more sources
Federated Learning With Spiking Neural Networks [PDF]
IEEE Transactions on Signal Processing, 2021 As neural networks get widespread adoption in resource-constrained embedded devices, there is a growing need for low-power neural systems. Spiking Neural Networks (SNNs)are emerging to be an energy-efficient alternative to the traditional Artificial Neural Networks (ANNs) which are known to be computationally intensive. From an application perspective,
Yeshwanth Venkatesha +3 more
openaire +2 more sources
Spiking Neural Networks: A Survey
IEEE Access, 2022 The field of Deep Learning (DL) has seen a remarkable series of developments with increasingly accurate and robust algorithms. However, the increase in performance has been accompanied by an increase in the parameters, complexity, and training and inference time of the models, which means that we are rapidly reaching a point where DL may no longer be ...
João D. Nunes +3 more
openaire +2 more sources
Agreement in Spiking Neural Networks
Journal of Computational Biology, 2022 We study the problem of binary agreement in a spiking neural network (SNN). We show that binary agreement on n inputs can be achieved with O(n) of auxiliary neurons. Our simulation results suggest that agreement can be achieved in our network in O(logn) time. We then describe a subclass of SNNs with a biologically plausible property, which we call size-
Kunev, Martin +2 more
openaire +3 more sources
Event-based backpropagation can compute exact gradients for spiking neural networks
Scientific Reports, 2021 Spiking neural networks combine analog computation with event-based communication using discrete spikes. While the impressive advances of deep learning are enabled by training non-spiking artificial neural networks using the backpropagation algorithm ...
Timo C. Wunderlich, Christian Pehle
doaj +1 more source