Networks of spiking neurons: the third generation of neural network models

By W. Maas. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Evolving Spiking Networks with Variable Resistive Memories (2014, background): “As the membrane potential may be considered a form of memory, such networks are able to produce temporally dynamic activation patterns, which potentially allows for increased computing power (Maass, 1996; Saggie-Wexler et al., 2006) when considering temporal problems (e.”
Broadcast and Weight: An Integrated Network For Scalable Photonic Spike Processing (2014, background): “expressiveness and efficiency of analog processing with the robustness of digital communication, and recurrent networks of spiking primitives possess rich algorithmic capabilities [2], [3].”
Evolving spike-timing-dependent plasticity for single-trial learning in robots (2003, background): “They have greater computational power than similar networks of threshold sigmoidal gates (Maass 1997).”
Spike-Timing Dependent Plasticity for Evolved Robots (2002, background): “They have comparatively greater computational power than similar networks of threshold sigmoidal gates (Maass, 1997).”
Photonics for artificial intelligence and neuromorphic computing (2020, background): “neural processing related to the timing of spikes) has been proposed as one of the keys to energy efficiency in biological nervous systems [85].”
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators (2016, background): “Spiking Neural Networks (SNNs) [57, 58, 59, 60] are popular in ASIC designs, largely due to their compact mapping onto fully-parallel hardware.”
Dynamic Stochastic Synapses as Computational Units (1997, methodology): “Results of computer simulations for longer spike trains can be found in Maass and Zador (1998) and Zador, Maass, and Natschläger (1998).”
Evolution of Plastic Learning in Spiking Networks via Memristive Connections (2012, background): “rived from [14]) and the Spike Response Model (SRM) [9]. The main justications for including SNN networks are (i) increased utility when compared to other network models e.g. the MLP [15] - shown in [16,17] (ii) current NC research focussing on spiking neurons as a basis of communication due to low ”
Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures (2019, background): “s of neural computing and to efﬁciently harness the machine learning algorithm in real-life (or mobile) applications. The concepts of SNN, which is often regarded as the 3rd generation neural network [37], are inspired by the biological neuronal mechanisms [9, 18, 6, 22] that can efﬁciently process ”