Neural networks : the official journal of the International Neural Network Society
Nov 4, 2019
In this paper, a novel kind of neural networks named fractional-order quaternion-valued bidirectional associative memory neural networks (FQVBAMNNs) is formulated. On one hand, applying Hamilton rules in quaternion multiplication which is essentially...
Nature communications
Sep 30, 2019
What is the physiological basis of long-term memory? The prevailing view in Neuroscience attributes changes in synaptic efficacy to memory acquisition, implying that stable memories correspond to stable connectivity patterns. However, an increasing b...
Neural networks : the official journal of the International Neural Network Society
Sep 19, 2019
Artificial neural networks (ANNs), a popular path towards artificial intelligence, have experienced remarkable success via mature models, various benchmarks, open-source datasets, and powerful computing platforms. Spiking neural networks (SNNs), a ca...
Neural networks : the official journal of the International Neural Network Society
Sep 9, 2019
An analysis of the literature shows that there are two types of non-memristive models that have been widely used in the modeling of so-called "memristive" neural networks. Here, we demonstrate that such models have nothing in common with the concept ...
Neural networks : the official journal of the International Neural Network Society
Aug 27, 2019
Deep Neural Networks (DNNs) have achieved extraordinary success in numerous areas. However, DNNs often carry a large number of weight parameters, leading to the challenge of heavy memory and computation costs. Overfitting is another challenge for DNN...
Proceedings of the National Academy of Sciences of the United States of America
Aug 20, 2019
Information coding by precise timing of spikes can be faster and more energy efficient than traditional rate coding. However, spike-timing codes are often brittle, which has limited their use in theoretical neuroscience and computing applications. He...
Computational intelligence and neuroscience
Aug 1, 2019
We explored several approaches to incorporate context information in the deep learning framework for text classification, including designing different attention mechanisms based on different neural network and extracting some additional features fro...
PloS one
Aug 1, 2019
From memorizing a musical tune to navigating a well known route, many of our underlying behaviors have a strong temporal component. While the mechanisms behind the sequential nature of the underlying brain activity are likely multifarious and multi-s...
PloS one
Jul 31, 2019
Previous work supports an age-specific impairment for recognition memory of pairs of words and other stimuli. The present study tested the generalization of an associative deficit across word, name, and nonword stimulus types in younger and older adu...
Advanced materials (Deerfield Beach, Fla.)
Jul 30, 2019
Sensory memory, formed at the beginning while perceiving and interacting with the environment, is considered a primary source of intelligence. Transferring such biological concepts into electronic implementation aims at achieving perceptual intellige...