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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
Vector Representation of Complex Numbers01:16

Vector Representation of Complex Numbers

Complex numbers, represented in Cartesian coordinates, can also be visualized as vectors. These vectors can be expressed in polar form, emphasizing their magnitude and angle. When a complex number is input into a function, the output is another complex number, highlighting the function's zero point from which the vector representation can originate.
Consider a function defined as the product of the complex factors in the numerator divided by the product of the complex factors in the denominator.
Linearization and Approximation01:26

Linearization and Approximation

Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
Piecewise-Defined Functions01:28

Piecewise-Defined Functions

Piecewise defined functions are mathematical models where different expressions define a function over distinct intervals of the domain. These functions are useful for representing systems with varying behaviors depending on input values.For example, the function:  uses a linear rule for inputs less than or equal to –1 and a quadratic rule for values greater than –1. Although it has two formulas, it still defines a single function.Another common type is the absolute value function, given...
Vector Algebra: Method of Components01:08

Vector Algebra: Method of Components

It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...
Encoding01:19

Encoding

Information enters the brain through encoding, which is the input of information into the memory system. Once sensory information is received from the environment, the brain labels or codes it. The information is then organized with similar information and connected to existing concepts. Encoding occurs through automatic processing and effortful processing.
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...

You might also read

Related Articles

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

Sort by
Same author

The Critical Period Microbiota Shape Brain Plasticity.

bioRxiv : the preprint server for biology·2026
Same author

Evaluating the Intelligence of large language models: A comparative study using verbal and visual IQ tests.

Computers in human behavior. Artificial humans·2026
Same author

The nBAF complex subunit CREST/SS18L1 regulates hippocampal memory processes via tyrosine 397 and histone acetyltransferase CBP.

Cell reports·2026
Same author

Circadian reprogramming by timed sodium intake reveals transcriptional pathways of daily salt handling in the colon.

Science advances·2026
Same author

Chronic intermittent hypoxia reshapes circadian metabolic architecture in a model of sleep apnea.

Science advances·2026
Same author

Decoding the Cardiac Immune Microenvironment and Fibroblast Crosstalk in Radiotherapy Combined with Immunotherapy-Induced Cardiac Fibrosis Based on Single-Cell Transcriptomic Analysis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: May 22, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Complex-valued autoencoders.

Pierre Baldi1, Zhiqin Lu

  • 1Department of Computer Science, UCI, Irvine, CA 92697-3435, USA. pfbaldi@ics.uci.edu

Neural Networks : the Official Journal of the International Neural Network Society
|May 25, 2012
PubMed
Summary
This summary is machine-generated.

This study introduces complex-valued linear autoencoders, unifying real and complex cases. The research reveals error landscapes with no local minima, offering insights into unsupervised learning and principal component analysis.

Related Experiment Videos

Last Updated: May 22, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Area of Science:

  • Machine Learning
  • Unsupervised Learning
  • Neural Networks

Background:

  • Autoencoders are unsupervised learning models minimizing input-output distortion.
  • Linear autoencoders use linear transformations; previously only real-valued versions were studied.
  • Understanding autoencoder error landscapes is crucial for algorithm development.

Purpose of the Study:

  • To analyze complex-valued linear autoencoders over the complex field.
  • To unify theoretical analysis for both real-valued and complex-valued linear autoencoders.
  • To investigate the error landscape, learning algorithms, and generalization properties.

Main Methods:

  • Developed a theoretical framework for complex-valued linear autoencoders using the L(2) norm.
  • Provided unified proofs for error function landscape invariance under transformations.
  • Derived iterative, convergent learning algorithms and analyzed generalization.

Main Results:

  • The error landscape is invariant under specific transformations and lacks local minima.
  • Global minima are linked to Principal Component Analysis (PCA).
  • Saddle points relate to orthogonal projections onto eigenvector subspaces.

Conclusions:

  • The framework clarifies autoencoder properties, connections to PCA, clustering, and information theory.
  • Offers insights into generalization and potential applications in deep architectures.
  • Provides a basis for classifying autoencoders and guiding future research.