AIMC Topic: Stochastic Processes

Clear Filters Showing 21 to 30 of 244 articles

Groundwater health risk assessment and its temporal and spatial evolution based on trapezoidal fuzzy number-Monte Carlo stochastic simulation: A case study in western Jilin province.

Ecotoxicology and environmental safety
The United States Environmental Protection Agency (USEPA) Four-step-Method (FSM) is a straightforward and extensively utilized tool for evaluating regional health risks, However, the complex and heterogeneous groundwater environment system causes gre...

T-distributed Stochastic Neighbor Network for unsupervised representation learning.

Neural networks : the official journal of the International Neural Network Society
Unsupervised representation learning (URL) is still lack of a reasonable operator (e.g. convolution kernel) for exploring meaningful structural information from generic data including vector, image and tabular data. In this paper, we propose a simple...

Unsupervised stochastic learning and reduced order modeling for global sensitivity analysis in cardiac electrophysiology models.

Computer methods and programs in biomedicine
BACKGROUND AND OBJECTIVE: Numerical simulations in electrocardiology are often affected by various uncertainties inherited from the lack of precise knowledge regarding input values including those related to the cardiac cell model, domain geometry, a...

Efficient and scalable prediction of stochastic reaction-diffusion processes using graph neural networks.

Mathematical biosciences
The dynamics of locally interacting particles that are distributed in space give rise to a multitude of complex behaviours. However the simulation of reaction-diffusion processes which model such systems is highly computationally expensive, the cost ...

Facial micro-expression recognition using stochastic graph convolutional network and dual transferred learning.

Neural networks : the official journal of the International Neural Network Society
Micro-expression recognition (MER) has drawn increasing attention due to its wide application in lie detection, criminal detection and psychological consultation. However, the best recognition accuracy on recent public dataset is still low compared t...

Robust Stochastic Neural Ensemble Learning With Noisy Labels for Thoracic Disease Classification.

IEEE transactions on medical imaging
Chest radiography is the most common radiology examination for thoracic disease diagnosis, such as pneumonia. A tremendous number of chest X-rays prompt data-driven deep learning models in constructing computer-aided diagnosis systems for thoracic di...

Fast synchronization control and application for encryption-decryption of coupled neural networks with intermittent random disturbance.

Neural networks : the official journal of the International Neural Network Society
In this paper, we design a new class of coupled neural networks with stochastically intermittent disturbances, in which the perturbation mechanism is different from other existed random neural networks. It is significant to construct the new models, ...

Tackling the curse of dimensionality with physics-informed neural networks.

Neural networks : the official journal of the International Neural Network Society
The curse-of-dimensionality taxes computational resources heavily with exponentially increasing computational cost as the dimension increases. This poses great challenges in solving high-dimensional partial differential equations (PDEs), as Richard E...

Decentralized stochastic sharpness-aware minimization algorithm.

Neural networks : the official journal of the International Neural Network Society
In recent years, distributed stochastic algorithms have become increasingly useful in the field of machine learning. However, similar to traditional stochastic algorithms, they face a challenge where achieving high fitness on the training set does no...

Gossip-based distributed stochastic mirror descent for constrained optimization.

Neural networks : the official journal of the International Neural Network Society
This paper considers a distributed constrained optimization problem over a multi-agent network in the non-Euclidean sense. The gossip protocol is adopted to relieve the communication burden, which also adapts to the constantly changing topology of th...