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

Assembly of Signaling Complexes

Assembly of Signaling Complexes

Multiprotein signaling complexes are formed in a dynamic process involving protein-protein interactions at the cytoplasmic domain of transmembrane receptors or enzymatic and non-enzymatic proteins associated with the receptor. These complexes ensure the activation and propagation of intracellular signals that regulate cell functions.
Interaction domains in cell signaling
Interaction domains recognize exposed features of their binding partners containing post-translationally modified sequences,...

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

Classification of Signals

Classification of Signals

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...

Reconstruction of Signal using Interpolation

Reconstruction of Signal using Interpolation

Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...

Hedgehog Signaling Pathway

Hedgehog Signaling Pathway

The Hedgehog gene (Hh) was first discovered due to its control of the growth of disorganized, hair-like bristles phenotype in Drosophila, much like hedgehog spines. Hh plays a crucial role in the development of organs and the maintenance of homeostasis in both invertebrates and vertebrates. However, while Drosophila has only one Hh protein, mammals have multiple functional Hedgehog proteins - Sonic (Shh), Desert (Dhh), and Indian Hedgehog (Ihh). All of these homologous proteins have adapted to...

Nonconscious Mimicry

Nonconscious Mimicry

Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.

You might also read

Related Articles

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

Sort by

Same author

Learning in Convolutional Neural Networks Accelerated by Transfer Entropy.

Entropy (Basel, Switzerland)·2021

Same author

Learning in Feedforward Neural Networks Accelerated by Transfer Entropy.

Entropy (Basel, Switzerland)·2020

Same author

Transfer Information Energy: A Quantitative Indicator of Information Transfer between Time Series.

Entropy (Basel, Switzerland)·2020

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 27, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Semiotic Aggregation in Deep Learning.

Bogdan Muşat^1,2, Răzvan Andonie^1,3

¹Department of Electronics and Computers, Transilvania University, 500036 Braşov, Romania.

Entropy (Basel, Switzerland)

|December 6, 2020

Summary

This summary is machine-generated.

This study introduces computational semiotics to analyze deep neural networks. By examining information concentration and spatial entropy in convolutional neural network layers, we offer new insights into feature abstraction and model interpretability.

Keywords:

convolutional neural networks deep learning saliency maps semiotics spatial entropy

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Nov 27, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Area of Science:

Artificial Intelligence
Computational Semiotics
Information Theory

Background:

Convolutional neural networks (CNNs) employ hierarchical layers for feature abstraction.
Understanding information concentration across these layers is crucial for interpreting CNN decision-making processes.
Existing methods lack a framework to analyze the semiotic nature of feature aggregation.

Purpose of the Study:

To apply computational semiotics to analyze the feature abstraction process in CNNs.
To investigate information concentration and spatial entropy in saliency maps across network layers.
To develop novel methods for interpreting and optimizing deep neural network architectures.

Main Methods:

Analysis of saliency maps using spatial entropy to quantify information content.
Application of semiotics principles, specifically superization, to understand sign aggregation in successive layers.
Development and application of a semiotic greedy technique for neural network architecture optimization.

Main Results:

Demonstrated a decrease in spatial entropy during superization, indicating information aggregation into supersigns.
Visualized the superization process, providing insights into the neural decision model.
Successfully optimized a neural model architecture using the proposed semiotic approach.

Conclusions:

Computational semiotics offers a novel and effective framework for interpreting deep neural networks.
Spatial entropy is a valuable metric for understanding information flow and feature abstraction in CNNs.
This work pioneers the use of semiotic principles for both analysis and optimization of AI models.