Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Classification of Signals01:30

Classification of Signals

869
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
869
State Space to Transfer Function01:21

State Space to Transfer Function

298
The conversion of state-space representation to a transfer function is a fundamental process in system analysis. It provides a method for transitioning from a time-domain description to a frequency-domain representation, which is crucial for simplifying the analysis and design of control systems.
The transformation process begins with the state-space representation, characterized by the state equation and the output equation. These equations are typically represented as:
298
State Space Representation01:27

State Space Representation

281
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
281
Signal and System01:26

Signal and System

1.1K
A signal x(t) is a set of data or a time function representing a variable of interest. Signals typically convey information about a phenomenon, such as atmospheric temperature, humidity, human voice, television images, a dog's bark, or birdsongs. More generally, a signal can be a function of more than one independent variable. For instance, images depend on horizontal and vertical positions and can be regarded as two-dimensional signals. However, this text will focus on one-dimensional...
1.1K
Transfer Function to State Space01:23

Transfer Function to State Space

393
State-space representation is a powerful tool for simulating physical systems on digital computers, necessitating the conversion of the transfer function into state-space form. Consider an nth-order linear differential equation with constant coefficients, like those encountered in an RLC circuit. The state variables are selected as the output and its n−1 derivatives. Differentiating these variables and substituting them back into the original equation produces the state equations.
In an...
393
Even and Odd Signals01:17

Even and Odd Signals

1.3K
An even signal, whether in continuous-time or discrete-time, is defined by its symmetry with its time-reversed version. Mathematically, this is represented as
1.3K

You might also read

Related Articles

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

Sort by
Same author

Potential Pitfalls With Automatic Sentiment Analysis: The Example of Queerphobic Bias.

Social science computer review·2023
Same author

Logic + probabilistic programming + causal laws.

Royal Society open science·2023
Same author

Breaking CAPTCHA with Capsule Networks.

Neural networks : the official journal of the International Neural Network Society·2022
Same author

Intention Recognition With ProbLog.

Frontiers in artificial intelligence·2022
Same author

Principles and Practice of Explainable Machine Learning.

Frontiers in big data·2021
Same author

Closed-Form Results for Prior Constraints in Sum-Product Networks.

Frontiers in artificial intelligence·2021

Related Experiment Video

Updated: Sep 7, 2025

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.8K

Signal Perceptron: On the Identifiability of Boolean Function Spaces and Beyond.

Miguel-Angel Mendez Lucero1, Rafael-Michael Karampatsis1, Enrique Bojorquez Gallardo1

  • 1The University of Edinburgh, Edinburgh, United Kingdom.

Frontiers in Artificial Intelligence
|June 20, 2022
PubMed
Summary

This study introduces a novel parallel machine using analytic sinusoids, capable of learning any non-linear Boolean function in a single layer. This new approach surpasses traditional perceptrons in learning speed and efficiency.

Keywords:
learning function spacesneural networksparallel machinesperceptronsignal perceptron

More Related Videos

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.9K
Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

23.2K

Related Experiment Videos

Last Updated: Sep 7, 2025

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.8K
Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.9K
Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

23.2K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Theory

Background:

  • The perceptron, a foundational model in artificial intelligence, is limited to learning linearly separable functions.
  • Minsky and Papert demonstrated that single-layer perceptrons cannot learn non-linear functions like XOR.
  • Existing parallel machine implementations face capacity limitations in learning complex functions.

Purpose of the Study:

  • To propose a novel, more powerful implementation of parallel machines.
  • To overcome the limitations of traditional perceptrons in learning non-linear Boolean functions.
  • To introduce a new mathematical tool utilizing analytic sinusoids for function representation.

Main Methods:

  • Developed a new parallel machine architecture based on analytic sinusoids.
  • Formulated an analytic signal representation for functions.
  • Utilized a single-layer mechanism for learning non-linear k-ary Boolean functions.

Main Results:

  • The proposed mechanism can learn any non-linear k-ary Boolean function with a single layer.
  • Demonstrated superior performance compared to single hidden layer multilayer perceptrons.
  • Achieved faster learning and required fewer parameters in Boolean function learning and image classification.

Conclusions:

  • The new analytic sinusoid-based parallel machine offers enhanced learning capacity.
  • This approach represents a significant advancement over traditional perceptron models.
  • The method shows practical advantages in computational efficiency and performance for complex learning tasks.