AIMC Topic: Neural Networks, Computer

Clear Filters Showing 8701 to 8710 of 31376 articles

Investigation of spatiotemporal distribution and formation mechanisms of ozone pollution in eastern Chinese cities applying convolutional neural network.

Journal of environmental sciences (China)
Severe ground-level ozone (O) pollution over major Chinese cities has become one of the most challenging problems, which have deleterious effects on human health and the sustainability of society. This study explored the spatiotemporal distribution c...

A deep learning pipeline for automated classification of vocal fold polyps in flexible laryngoscopy.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery
PURPOSE: To develop and validate a deep learning model for distinguishing healthy vocal folds (HVF) and vocal fold polyps (VFP) on laryngoscopy videos, while demonstrating the ability of a previously developed informative frame classifier in facilita...

Human shape representations are not an emergent property of learning to classify objects.

Journal of experimental psychology. General
Humans are particularly sensitive to relationships between parts of objects. It remains unclear why this is. One hypothesis is that relational features are highly diagnostic of object categories and emerge as a result of learning to classify objects....

RepCo: Replenish sample views with better consistency for contrastive learning.

Neural networks : the official journal of the International Neural Network Society
Contrastive learning methods aim to learn shared representations by minimizing distances between positive pairs, and maximizing distances between negative pairs in the embedding space. To achieve better performance of contrastive learning, one of the...

Bifurcations of a delayed fractional-order BAM neural network via new parameter perturbations.

Neural networks : the official journal of the International Neural Network Society
This paper makes a new breakthrough in deliberating the bifurcations of fractional-order bidirectional associative memory neural network (FOBAMNN). In the beginning, the corresponding bifurcation results are established according to self-regulating p...

An exact mapping from ReLU networks to spiking neural networks.

Neural networks : the official journal of the International Neural Network Society
Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propo...

Investigation of machine learning algorithms for taxonomic classification of marine metagenomes.

Microbiology spectrum
Taxonomic profiling of microbial communities is essential to model microbial interactions and inform habitat conservation. This work develops approaches in constructing training/testing data sets from publicly available marine metagenomes and evaluat...

A scalable second order optimizer with an adaptive trust region for neural networks.

Neural networks : the official journal of the International Neural Network Society
We introduce Tadam (Trust region ADAptive Moment estimation), a new optimizer based on the trust region of the second-order approximation of the loss using the Fisher information matrix. Despite the enhanced gradient estimations offered by second-ord...

Learning heterogeneous delays in a layer of spiking neurons for fast motion detection.

Biological cybernetics
The precise timing of spikes emitted by neurons plays a crucial role in shaping the response of efferent biological neurons. This temporal dimension of neural activity holds significant importance in understanding information processing in neurobiolo...

NNP/MM: Accelerating Molecular Dynamics Simulations with Machine Learning Potentials and Molecular Mechanics.

Journal of chemical information and modeling
Machine learning potentials have emerged as a means to enhance the accuracy of biomolecular simulations. However, their application is constrained by the significant computational cost arising from the vast number of parameters compared with traditio...