Results 81 to 90 of about 22,581 (258)

Spike-based computation using classical recurrent neural networks

Neuromorphic Computing and Engineering
Spiking neural networks (SNNs) are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes.
Florent De Geeter, Damien Ernst, Guillaume Drion   +2 more
doaj   +1 more source

Optoelectronic Nanofluidic Neural Networks for Ionic Computing

Advanced Materials, EarlyView.
An ion‐based optoelectronic nanofluidic memristor enables neuromorphic computing in aqueous environments. With tunable ionic memory and multimodal synaptic plasticity, it realizes densely connected ionic neural networks capable of image classification, motion prediction, logic computation, and real‐time in‐sensor computing, advancing fully connected ...
Yaxin Huang, Zhiyuan Du, Changjin Wu, Binglin Zeng, Yingnan Cao, Mingliang Li, Liren Zhang, Qingxin Guo, Chao Huang, Can Li, Jinyao Tang   +10 more
wiley   +1 more source

Efficient Deep Spiking Neural Network for Complex EEG Signals

IEEE Access
Spiking neural networks (SNNs) offer a biologically inspired, energy-efficient alternative to conventional artificial neural networks (ANNs). However, deep SNNs struggle to process complex EEG signals because their spike-based representations are sparse ...
Elham Amirizadeh, Reza Boostani
doaj   +1 more source

Electrically Coded Retinomorphic Spectrophotodetector

Advanced Materials, EarlyView.
Self‐powered retinomorphic pyro‐photodetector is demonstrated that avoids machine‐learning post‐processing and covers 365–940 nm. Electrostatic balancing of built‐in potential produces an electrical wavelength code, delivering <3 nm wavelength decoding accuracy with ∼46 µs response.
Mohit Kumar, Hyunmin Dang, Hyungtak Seo
wiley   +1 more source

Spiking Neural Network Pressure Sensor

Neural 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, Ireneusz Brzozowski, Szymon Janusz   +2 more
openaire   +3 more sources

Soft Skins With Reversible Thickness Morphing: Materials, Mechanisms, and Applications

Advanced Materials, EarlyView.
Evolution of electronic skin (e‐skin) technologies toward adaptive, multifunctional soft skins. Phase I highlights early rigid and discrete sensory interfaces. Phase II shows the transition toward flexible, stretchable, and large‐area e‐skin. Phase III captures the emergence of computational e‐skin.
Oliver Ozioko, Chiamaka Akah, Ravinder Dahiya   +2 more
wiley   +1 more source

Research on SNN Learning Algorithms and Networks Based on Biological Plausibility

IEEE Access
Spiking Neural Networks, inspired by the brain’s neuronal information processing mech- anisms, utilize sparse, event-based spike signals to emulate biological computation.
Bingqiang Huo, Fang Li, Siyu Peng, Hongwei Chen, Sudan Xin, Hongjun Wang   +5 more
doaj   +1 more source

Hyperdimensional decoding of spiking neural networks

Neuromorphic 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, Luca Peres, Oliver Rhodes   +2 more
openaire   +3 more sources

Metal Oxide Nano‐Interface Boosting the Deep Ultraviolet Adjustable Noise‐Filtering In‐Sensor Computing

Advanced Materials, EarlyView.
We show that sol‐gel‐fractured indium–magnesium oxide combines deep‐ultraviolet responsivity, high carrier mobility, and an excellent memory dynamic range. This unique materials platform enables deep‐ultraviolet long‐afterglow light‐emitting devices with multifunctional integration.
Zhongshi Ju, Peng Li, Jingsong Yuan, Boyuan Yu, Bin Han, Yusheng Chen, Jiangang Ma, Haiyang Xu, Yichun Liu, Paolo Samorì   +9 more
wiley   +1 more source

Fast learning without synaptic plasticity in spiking neural networks

Scientific Reports
Spiking neural networks are of high current interest, both from the perspective of modelling neural networks of the brain and for porting their fast learning capability and energy efficiency into neuromorphic hardware. But so far we have not been able to
Anand Subramoney, Guillaume Bellec, Franz Scherr, Robert Legenstein, Wolfgang Maass   +4 more
doaj   +1 more source