Recurrent neural networks are able to store information about previous as well as current inputs. This “memory” allows them to solve temporal problems such as language recognition and sequence prediction, and provide memory elements for larger cognitive networks. It is generally understood that there is an (increasing) relationship between the number of nodes (and connections) in a network, the...

We developed a method called Time-Slicing [1] for the analysis of the speech signal. It enables a neural network to recognize connected speech as it comes, without having to fit the input signal into a fixed time-format, nor label or segment it phoneme by phoneme. The neural network produces an immediate hypothesis of the recognized phoneme and its size is small enough to run even on a PC. To i...

Forecasting a hydrologic time series has been one of the most complicated tasks owing to the wide range of data, the uncertainties in the parameters influencing the time series and also due to the non availability of adequate data. Recently Artificial Neural Networks (ANN) have become quite popular in time series forecasting in various fields. This paper demonstrates the use of ANN to forecast ...

Resonance structures and features are ubiquitous in optical science. However, capturing their time dynamics real-world scenarios suffers from long data acquisition low analysis accuracy due to slow convergence limited windows. Here we report a physics-informed recurrent neural network forecast the time-domain response of resonances infer corresponding resonance frequencies by acquiring fraction...

A new adaptive learning rate is proposed based on the Lya-punov stability theory for training the Ring-Structured Recurrent Network (RSRN). The adaptive rate is a suucient condition to guarantee the stability and the most rapid convergence of the RSRN dynamic backpropagation algorithm, and it is easily determined in a direct and non-trial manner. Examples of training the RSRN to predict time se...

Presents a recurrent neural network for solving the Sylvester equation with time-varying coefficient matrices. The recurrent neural network with implicit dynamics is deliberately developed in the way that its trajectory is guaranteed to converge exponentially to the time-varying solution of a given Sylvester equation. Theoretical results of convergence and sensitivity analysis are presented to ...

Demand prediction for humanitarian logistics is a complex problem with immediate real-world consequences. This paper examines fuel demand during two regional crisis events and the supply chain operated by US Government as part of Operation Unified Response. Because typical machine learning algorithms require large amounts training data, our methods predictive analysis depend on rapid model wher...

Critical dynamics research of recurrent neural networks (RNNs) is very meaningful in both theoretical importance and practical significance. Due to the essential difficulty in analysis, there were only a few contributions concerning it. In this paper, we devote to study the critical dynamics behaviors for RNNs with general forms. By exploring some intrinsic features processed naturally by the n...

A networked control system (NCS) is a control system in which plants, sensors, controllers, and actuators are connected through communication networks. In this paper, as one of the design problems for NCSs, we consider optimal sampled-data control of linear systems with uncertain input delay and uncertain sampling period. First, an input delay system is transformed into a discrete-time system w...