Results 141 to 150 of about 24,472 (312)

A systematic method for configuring VLSI networks of spiking neurons

open access: yes, 2011
Neftci E, Chicca E, Indiveri G, Douglas RJ. A systematic method for configuring VLSI networks of spiking neurons. Neural Computation. 2011;23(10):2457-2497.An increasing number of research groups are developing custom hybrid analog/digital very large ...
Rodney Douglas   +11 more
core   +1 more source

An On‐Demand Neuromorphic Vision System Enabled by a Multi‐Paradigm Neuromorphic Device and Hierarchical Reconfigurability Designed from Device to System Level

open access: yesAdvanced Science, EarlyView.
An on‐demand ultra‐reconfigurable intelligent vision system with hierarchical reconfigurability from device to system levels is demonstrated. Through co‐design of a multi‐paradigm device, reconfigurable circuits, and adaptive system architecture/algorithms, the system enables seamless switching among spiking, non‐spiking, neuromorphic imaging (NI), and
Biyi Jiang   +7 more
wiley   +1 more source

A Pollen‐Enhanced Bionic Mechanoreceptor Induced by Asymmetric Ionic Convection in Hydrogel for Sensory‐Augmented Prostheses

open access: yesAdvanced Science, EarlyView.
This work proposed a pollen‐enhanced bionic mechanoreceptor based on ionic convection. Leveraging the ion anchoring effect of the pollen particle, the output performance could be ∼12 times higher than the original state. By employing deep learning models as AI brains, the feasibility of a sensory‐augmented prosthesis consisting of a pollen‐enhanced ...
Zi Hao Guo   +7 more
wiley   +1 more source

Spike-timing-dependent plasticity and synaptic consolidation in Hfo₂ memristors for adaptive neuromorphic computing

open access: yesNeuromorphic Computing and Engineering
In this work, we demonstrate the potential of HfO₂-based memristors as artificial synapses capable of reproducing biologically plausible spike-timing-dependent plasticity (STDP).
Mostafa Shooshtari   +3 more
doaj   +1 more source

Neuromorphic engineering: neuromimetic computation for understanding the brain [PDF]

open access: yes, 2014
Neuromorphic engineering attempts to understand the computational properties of neural processing systems by building electronic circuits and systems that emulate the principles of computation in the neural systems.
Abbott, Derek   +2 more
core  

Neuromorphic Systems: past, present and future

open access: yes, 2010
Neuromorphic systems are implementations in silicon of elements of neural systems. The idea of electronic implementation is not new, but modern microelectronics has provided opportunities for producing systems for both sensing and neural modelling that ...
Smith, Leslie
core   +1 more source

Polarization‐Enabled Piezoelectric Tellurium–Selenium (TexSe1–x) Thin Films for Memory Switching and Artificial Synaptic Functions

open access: yesAdvanced Science, EarlyView.
Here, we demonstrate and investigate polarization‐enabled electromechanical responses in cryogenic physical vapor deposition (cryogenic PVD)‐deposited TexSe1‐x thin films, a tellurium‐based compound with a tunable bandgap and enhanced non‐centrosymmetry.
Chia‐Chen Chung   +16 more
wiley   +1 more source

High‐Endurance STO:YSZ Optoelectronic Memristors with Vertically Aligned Nanocomposite Structure for Edge Detection

open access: yesAdvanced Science
Edge detection plays a critical role in cutting‐edge domains such as real‐time monitoring and automatic driving, with optoelectronic device‐based real‐time image processing garnering significant attention. However, the poor endurance and unstable optical
Jiacheng Wang   +11 more
doaj   +1 more source

Ferroelectric Devices for In‐Memory and In‐Sensor Computing

open access: yesAdvanced Science, EarlyView.
Inspired by biological systems, in‐memory and in‐sensor computing overcome von Neumann bottlenecks. Ferroelectric devices can mimic synaptic functions and sense stimuli like light or force, therefore are ideal for these paradigms. This review introduces the ferroelectric devices applied for in‐memory and in‐sensor computing, covering their structures ...
Hong Fang   +5 more
wiley   +1 more source

Time Series Forecasting via Derivative Spike Encoding and Bespoke Loss Functions for Spiking Neural Networks

open access: yesComputers
The potential of neuromorphic (NM) solutions often lies in their low-SWaP (Size, Weight, and Power) capabilities, which often drive their application to domains that could benefit from this.
Davide Liberato Manna   +4 more
doaj   +1 more source

Home - About - Disclaimer - Privacy