AIMC Topic: Stochastic Processes

Clear Filters Showing 31 to 40 of 251 articles

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...

Mean square exponential stabilization analysis of stochastic neural networks with saturated impulsive input.

Neural networks : the official journal of the International Neural Network Society
The exponential stabilization of stochastic neural networks in mean square sense with saturated impulsive input is investigated in this paper. Firstly, the saturated term is handled by polyhedral representation method. When the impulsive sequence is ...

A novel framework of prescribed time/fixed time/finite time stochastic synchronization control of neural networks and its application in image encryption.

Neural networks : the official journal of the International Neural Network Society
In this paper, we investigate a novel framework for achieving prescribed-time (PAT), fixed-time (FXT) and finite-time (FNT) stochastic synchronization control of semi-Markov switching quaternion-valued neural networks (SMS-QVNNs), where the setting t...

Reachable set estimation and stochastic sampled-data exponential synchronization of Markovian jump neural networks with time-varying delays.

Neural networks : the official journal of the International Neural Network Society
In this paper, the stochastic sampled-data exponential synchronization problem for Markovian jump neural networks (MJNNs) with time-varying delays and the reachable set estimation (RSE) problem for MJNNs subjected to external disturbances are investi...

Constrained disorder principle-based variability is fundamental for biological processes: Beyond biological relativity and physiological regulatory networks.

Progress in biophysics and molecular biology
The constrained disorder principle (CDP) defines systems based on their degree of disorder bounded by dynamic boundaries. The principle explains stochasticity in living and non-living systems. Denis Noble described the importance of stochasticity in ...

Robust exponential stability of discrete-time uncertain impulsive stochastic neural networks with delayed impulses.

Neural networks : the official journal of the International Neural Network Society
This paper is devoted to the study of the robust exponential stability (RES) of discrete-time uncertain impulsive stochastic neural networks (DTUISNNs) with delayed impulses. Using Lyapunov function methods and Razumikhin techniques, a number of suff...

Stochastic Stability of Markovian Neural Networks With Generally Hybrid Transition Rates.

IEEE transactions on neural networks and learning systems
This article studies the problem of the stability for Markovian neural networks (MNNs) with time delay. The transition rate is considered to be generally hybrid, which treats those existing ones as its special cases. The introduced generally hybrid t...