Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Rectangular and Triangular Pulse Function

Rectangular and Triangular Pulse Function

The unit rectangular pulse function is mathematically represented by a rectangular function centered at the origin with a height of one unit. This function is defined by two parameters: T, which specifies the center location of the pulse along the time axis, and τ, which determines the pulse duration.
For example, consider a rectangular pulse with a 5V amplitude, a 3-second duration, and centered at t=2 seconds. This pulse can be expressed using the rectangular function, written as,

Prediction Intervals

Prediction Intervals

The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.

Discrete-Time Fourier Series

Discrete-Time Fourier Series

The Discrete-Time Fourier Series (DTFS) is a fundamental concept in signal processing, serving as the discrete-time counterpart to the continuous-time Fourier series. It allows for the representation and analysis of discrete-time periodic signals in terms of their frequency components. Unlike its continuous counterpart, which utilizes integrals, the calculation of DTFS expansion coefficients involves summations due to the discrete nature of the signal.
For a discrete-time periodic signal x[n]...

Residuals and Least-Squares Property

Residuals and Least-Squares Property

The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...

Linear time-invariant Systems

Linear time-invariant Systems

A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...

BIBO stability of continuous and discrete -time systems

BIBO stability of continuous and discrete -time systems

System stability is a fundamental concept in signal processing, often assessed using convolution. For a system to be considered bounded-input bounded-output (BIBO) stable, any bounded input signal must produce a bounded output signal. A bounded input signal is one where the modulus does not exceed a certain constant at any point in time.
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system....

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Uniform zinc oxide nanowire arrays grown on nonepitaxial surface with general orientation control.

Nano letters·2013

Same author

[American head and neck surgery progress of in 2012].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2013

Same author

A compact thermo-optical multimode-interference silicon-based 1 × 4 nano-photonic switch.

Optics express·2013

Same author

Experimental demonstration of 110-Gb/s unsynchronized band-multiplexed superchannel coherent optical OFDM/OQAM system.

Optics express·2013

Same author

Potentially functional variants of p14ARF are associated with HPV-positive oropharyngeal cancer patients and survival after definitive chemoradiotherapy.

Carcinogenesis·2013

Same author

Enhanced molecular transport in hierarchical silicalite-1.

Langmuir : the ACS journal of surfaces and colloids·2013

Search research articles

Related Experiment Video

Updated: Jul 8, 2025

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

Fractional Tensor Recurrent Unit (fTRU): A Stable Forecasting Model With Long Memory.

Hejia Qiu, Chao Li, Ying Weng

IEEE Transactions on Neural Networks and Learning Systems

|December 15, 2023

Summary

This summary is machine-generated.

We introduce a fractional tensor recurrent unit (fTRU) for advanced recurrent neural networks (RNNs). This model enhances long memory and stability in sequence tasks, outperforming existing RNNs in forecasting.

More Related Videos

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Published on: July 3, 2020

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy

Published on: July 9, 2017

Related Experiment Videos

Last Updated: Jul 8, 2025

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Published on: July 3, 2020

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy

The Optical Fractionator Technique to Estimate Cell Numbers in a Rat Model of Electroconvulsive Therapy

Published on: July 9, 2017

Area of Science:

Artificial Intelligence
Machine Learning
Dynamical Systems

Background:

Tensor recurrent models are nonlinear dynamical systems utilizing tensor products.
Existing models have limited studies on long memory and stability for sequence tasks.
Advanced recurrent neural networks (RNNs) often employ these models.

Purpose of the Study:

To propose a fractional tensor recurrent model (fTRU) for improved sequence tasks.
To extend the tensor degree from discrete to continuous domains for better learnability.
To balance long memory properties with model stability.

Main Methods:

Developed a fractional tensor recurrent unit (fTRU).
Extended tensor degree from discrete to continuous domains.
Theoretically analyzed the trade-off between memory and stability.

Main Results:

The proposed fTRU achieves competitive performance in forecasting tasks.
Demonstrated long memory and stable dynamical behaviors.
Experimental results show advantages over various advanced RNNs.

Conclusions:

The fTRU effectively balances long memory and stability in recurrent neural networks.
The fractional extension enables effective learning from diverse datasets.
This model offers a promising advancement for sequence modeling and forecasting.