Results 111 to 120 of about 4,242,343 (297)

Evolutionary spiking neural networks: a survey

open access: yesJournal of Membrane Computing
Spiking neural networks (SNNs) are gaining increasing attention as potential computationally efficient alternatives to traditional artificial neural networks(ANNs). However, the unique information propagation mechanisms and the complexity of SNN neuron models pose challenges for adopting traditional methods developed for ANNs to SNNs.
Shuaijie Shen   +8 more
openaire   +4 more sources

Hardware implementation of stochastic spiking neural networks [PDF]

open access: yes
[eng] Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bioinspired nature and by a higher computational capacity with respect to other neural models.
Rossello, J.L.   +3 more
core   +1 more source

Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction

open access: yes, 2023
Spiking neural networks (SNNs) can be used in low-power and embedded systems e.g. neuromorphic chips due to their event-based nature. They preserve conventional artificial neural networks (ANNs) properties with lower computation and memory costs.
Fatemeh Sadat Tabatabaei Far   +15 more
core   +1 more source

NeuroVisio SyncPatch: A Skin‐Conformal Multimodal EMG–Motion Sensing Platform for Quantitative Neuromuscular Rehabilitation and Performance Monitoring

open access: yesAdvanced Healthcare Materials, EarlyView.
NeuroVisio SyncPatch integrates skin‐conformal electromyography (EMG) electrodes with camera‐tracked markers to jointly assess muscle activity and three‐dimensional knee kinematics during rehabilitation. Parallel feedback pathways provide real‐time kinematic guidance during movement and post‐trial neuromuscular feedback.
Bohyung Choi   +11 more
wiley   +1 more source

Real-time inference in a VLSI spiking neural network [PDF]

open access: yes, 2012
The ongoing motor output of the brain depends on its remarkable ability to rapidly transform and fuse a variety of sensory streams in real-time.
Matthew Cook   +16 more
core   +1 more source

Training multi-layer spiking neural networks with plastic synaptic weights and delays

open access: yesFrontiers in Neuroscience
Spiking neural networks are usually considered as the third generation of neural networks, which hold the potential of ultra-low power consumption on corresponding hardware platforms and are very suitable for temporal information processing. However, how
Jing Wang
doaj   +1 more source

Hemocompatible Glycogen‐Tissue Plasminogen Activator Complexes for Enhanced Blood Clot Dissolution

open access: yesAdvanced Healthcare Materials, EarlyView.
Glycogen–heparin‐cRGD nanoparticles enable targeted delivery of tissue plasminogen activator (tPA) to thrombi through activated platelet recognition. The hemocompatible hybrids minimize interactions with blood and immune cells while retaining enzymatic biodegradability.
Nadiia Davydiuk   +6 more
wiley   +1 more source

Spiking Neural Network Pressure Sensor

open access: yesNeural Computation
Abstract Von Neumann architecture requires information to be encoded as numerical values. For that reason, artificial neural networks running on computers require the data coming from sensors to be discretized. Other network architectures that more closely mimic biological neural networks (e.g., spiking neural networks) can be simulated ...
Michal Markiewicz   +2 more
openaire   +4 more sources

Ferroelectric Quantum Dots for Retinomorphic In‐Sensor Computing

open access: yesAdvanced Materials, EarlyView.
This work has provided a protocol for fabricating retinomorphic phototransistors by integrating ferroelectric ligands with quantum dots. The resulting device combines ferroelectricity, optical responsiveness, and low‐power operation to enable adaptive signal amplification and high recognition accuracy under low‐light conditions, while supporting ...
Tingyu Long   +26 more
wiley   +1 more source

Hyperdimensional decoding of spiking neural networks

open access: yesNeuromorphic Computing and Engineering
Abstract This work presents a novel spiking neural network (SNN) decoding method, combining SNNs with hyperdimensional computing (HDC). This decoding method is designed to achieve high accuracy, high noise robustness, low inference latency and low energy consumption. Compared to analogous architectures decoded with existing approaches,
Cedrick Kinavuidi   +2 more
openaire   +4 more sources

Home - About - Disclaimer - Privacy