Related papers: Self-reset schemes for Magnetic domain wall-based …
Artificial neural networks (ANNs) have been extensively used for the description of problems arising from biological systems and for constructing neuromorphic computing models. The third generation of ANNs, namely, spiking neural networks…
In timing-based neural codes, neurons have to emit action potentials at precise moments in time. We use a supervised learning paradigm to derive a synaptic update rule that optimizes via gradient ascent the likelihood of postsynaptic firing…
Excitable optoelectronic devices represent one of the key building blocks for implementation of artificial spiking neurons in neuromorphic (brain-inspired) photonic systems. This work introduces and experimentally investigates an…
Redundant information transfer in a neural network can increase the complexity of the deep learning model, thus increasing its power consumption. We introduce in this paper a novel spiking neuron, termed Variable Spiking Neuron (VSN), which…
Spiking neural networks (SNNs) offer biologically inspired computation but remain underexplored for continuous regression tasks in scientific machine learning. In this work, we introduce and systematically evaluate Quadratic…
The neural dynamics generating sensory, motor, and cognitive functions are commonly understood through field theories for neural population activity. Classic neural field theories are derived from highly simplified models of individual…
Nanoscale self-localized topological spin textures, such as domain walls and skyrmions, are of interest for the fundamental physics of magnets and spintronics applications. Ferrimagnets (FiMs), in the region close to the angular momentum…
We introduce an algorithm to do backpropagation on a spiking network. Our network is "spiking" in the sense that our neurons accumulate their activation into a potential over time, and only send out a signal (a "spike") when this potential…
In this work, we introduce an optoelectronic spiking artificial neuron capable of operating at ultrafast rates ($\approx$ 100 ps/optical spike) and with low energy consumption ($<$ pJ/spike). The proposed system combines an excitable…
Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning…
The current-driven motion of magnetic domain walls (DWs) is the working principle of magnetic racetrack memories. In this type of spintronic technology, high current densities are used to propel DW motion in magnetic nanowires, causing…
In spiking neural networks (SNN), at each node, an incoming sequence of weighted Dirac pulses is converted into an output sequence of weighted Dirac pulses by a leaky-integrate-and-fire (LIF) neuron model based on spike aggregation and…
Inspired by the brain's information processing using binary spikes, spiking neural networks (SNNs) offer significant reductions in energy consumption and are more adept at incorporating multi-scale biological characteristics. In SNNs,…
Spiking neural networks (SNNs) present a promising computing paradigm for neuromorphic processing of event-based sensor data. The resonate-and-fire (RF) neuron, in particular, appeals through its biological plausibility, complex dynamics,…
This paper predicts the ability to externally control the firing times of a cortical neuron whose behavior follows the Izhikevich neuron model. The Izhikevich neuron model provides an efficient and biologically plausible method to track a…
Memristors have been suggested as neuromorphic computing elements. Spike-time dependent plasticity and the Hodgkin-Huxley model of the neuron have both been modelled effectively by memristor theory. The d.c. response of the memristor is a…
We simulate automotion, the spontaneous transport of a magnetic domain wall under the influence of demagnetization and magnetic anisotropy, in nanoscale spintronic interconnects. In contrast to spin transfer driven magnetic domain wall…
Spiking neural networks (SNN) are able to learn spatiotemporal features while using less energy, especially on neuromorphic hardware. The most widely used spiking neuron in deep learning is the Leaky Integrate and Fire (LIF) neuron. LIF…
We address the problem of learning feedback control where the controller is a network constructed solely of deterministic spiking neurons. In contrast to previous investigations that were based on a spike rate model of the neuron, the…
Resonate-and-Fire (RF) neurons are an interesting complementary model for integrator neurons in spiking neural networks (SNNs). Due to their resonating membrane dynamics they can extract frequency patterns within the time domain. While…