Pulsed Neural Networks

By Christopher Bishop. 1998

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

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “mputational relations among various nuclei, pathways, and learning processes (Krichmar, 2008; Vitay and Hamker, 2010; Schroll and Hamker, 2015). Finally, plasticity rules for spiking neural networks (Maass and Bishop, 2001) aim to demonstrate unique learning mechanisms that emerge from spiking dynam”
Artificial neural networks in hardware: A survey of two decades of progress (2010, unknown): “Networks of I&F neurons exhibit a wide range of capabilities including feature binding, segmentation, pattern recognition, onset detection, and input prediction [131].”
Rhythms of the brain (2006, background): “These ideas have their roots in early modeling attempts (Marr, 1971; Kohonen, 1984; Kaverna, 1988; Maas and Bishop, 1999).”
Generalized integrate-and-fire models of neuronal activity approximate spike trains of a detailed model to a high degree of accuracy. (2004, methodology): “…spiking neuron models such as integrate-and-fire (IF) models (Geisler and Goldberg 1966; Hill 1936; Stein 1965; Tuckwell 1988) are highly popular and have been used to discuss aspects of neural coding, memory, or network dynamics (for a review, see Gerstner and Kistler 2002; Maass and Bishop 1998).”
Neuronal Plasticity and Temporal Adaptivity: GasNet Robot Control Networks (2002, background): “…falls squarely into a larger class that is likely to contain other networks with temporally modifiable properties, such as continuous time recurrent networks (Beer & Gallagher, 1992), pulsed neural networks (Maass & Bishop, 1999), and networks with time-lagged synaptic activity (Harvey, 1993).”
The evolvability of artificial neural net-works for robot control (2002, methodology): “” On this fundamental principle of temporal adaptivity, the GasNet neural network class falls squarely into a larger class that is likely to contain other networks with temporally modifiable properties, such as continuous time recurrent networks (Beer and Gallagher, 1992), pulsed neural networks (Ma”
Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting (2010, methodology): “In this context, hardware VLSI emulators of SNN become an interesting topic of investigation (we refer to Maass & Bishop, 1999, for an overview).”
A Novel Approach for the Implementation of Large Scale Spiking Neural Networks on FPGA Hardware (2005, background): “Such research is motivated by the desire to form a more comprehensive understanding of information processing in biological networks and to investigate how this understanding could be used to improve traditional information processing techniques [2].”
Evolving spiking neural network controllers for autonomous robots (2004, background): “Not only are implementations of SNNs difficult to hand craft [2] but the learning algorithms developed for SNNs are often restricted to very simple and application specific architectures [7].”
From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation (2012, background): “The reconfigure-and-saturate Hebbian dynamics hold equally with a simple spiking neuron model (Wilson, 1999; Maass and Bishop, 1999; Gerstner and Kistler, 2002b).”
Stochastic Neural Computation I: Computational Elements (2001, methodology): “Part of the reason for this is that there are so many different ways of implementing pulsed neural networks in analog form [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14].”