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

Neural Circuits01:25

Neural Circuits

2.2K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.2K
Block Diagram Reduction01:22

Block Diagram Reduction

391
The process of deriving the transfer function of a control system often involves reducing its block diagram to a single block. This simplification can be achieved through a series of strategic operations, including relocating branch points and comparators. These operations preserve the overall function of the system while allowing for easier manipulation and combination of blocks.
The first step in this process is the identification and relocation of a branch point. A branch point, where a...
391
Network Function of a Circuit01:25

Network Function of a Circuit

469
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
469
Relation between Mathematical Equations and Block Diagrams01:20

Relation between Mathematical Equations and Block Diagrams

2.6K
In a spring-mass-damper system, the second-order differential equation describes the dynamic behavior of the system. When transformed into the Laplace domain under zero initial conditions, this equation can be effectively analyzed and manipulated. The transformation into the Laplace domain converts differential equations into algebraic equations, simplifying the process of isolating the output.
2.6K

You might also read

Related Articles

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

Sort by
Same author

Probing Hydrogen Activation in a Dimetal Dihydride Complex by Symmetric Exchange with Parahydrogen.

Journal of the American Chemical Society·2026
Same author

Chemical hydrodynamics of nuclear spin states.

Science advances·2025
Same author

Simulation of pulsed dynamic nuclear polarization in the steady state.

The Journal of chemical physics·2025
Same author

Leveraging relaxation-optimized <sup>1</sup>H-<sup>13</sup>C<sub>F</sub> correlations in 4-<sup>19</sup>F-phenylalanine as atomic beacons for probing structure and dynamics of large proteins.

Nature chemistry·2025
Same author

Instrumental distortions in quantum optimal control.

The Journal of chemical physics·2025
Same author

Protein NMR assignment by isotope pattern recognition.

Science advances·2024

Related Experiment Video

Updated: Nov 19, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

285

Neural network interpretation using descrambler groups.

Jake L Amey1, Jake Keeley1, Tajwar Choudhury1

  • 1School of Chemistry, University of Southampton, Southampton SO17 1BJ, United Kingdom.

Proceedings of the National Academy of Sciences of the United States of America
|January 27, 2021
PubMed
Summary

We developed a group-theoretical method to make deep neural networks interpretable. Applied to a digital signal processing network, it revealed sophisticated, human-readable internal transformations, enhancing trust in AI for scientific applications.

Keywords:
digital signal processingelectron spin resonanceinterpretabilitymachine learning

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.6K
Deciphering Axonal Pathways of Genetically Defined Groups of Neurons in the Chick Neural Tube Utilizing in ovo Electroporation
07:55

Deciphering Axonal Pathways of Genetically Defined Groups of Neurons in the Chick Neural Tube Utilizing in ovo Electroporation

Published on: May 2, 2010

9.5K

Related Experiment Videos

Last Updated: Nov 19, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

285
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.6K
Deciphering Axonal Pathways of Genetically Defined Groups of Neurons in the Chick Neural Tube Utilizing in ovo Electroporation
07:55

Deciphering Axonal Pathways of Genetically Defined Groups of Neurons in the Chick Neural Tube Utilizing in ovo Electroporation

Published on: May 2, 2010

9.5K

Area of Science:

  • Artificial Intelligence
  • Computational Science
  • Digital Signal Processing

Background:

  • Deep neural networks (DNNs) lack interpretability, hindering trust, especially in scientific computing and digital signal processing (DSP).
  • The 'black box' nature of DNNs, caused by scrambled inner-layer signaling during backpropagation, limits their application in abstract mathematical transformations.

Purpose of the Study:

  • To develop a group-theoretical procedure for rendering DNN inner-layer signaling human-readable.
  • To enhance trust and interpretability of DNNs in scientific and DSP applications.

Main Methods:

  • A novel group-theoretical procedure was devised to analyze and organize inner-layer signaling in DNNs.
  • The method assumes that interpretable features like smoothness and locality exist within the network's transformations.
  • The procedure was applied to DEERNet, a DSP network used in electron spin resonance (ESR).

Main Results:

  • The proposed method successfully 'descrambled' the DEERNet, revealing its internal workings.
  • The network spontaneously learned sophisticated DSP components, including bandpass and notch filters, frequency rescaling, and multiplexing.
  • Novel transformations such as group embedding and spectral filtering regularization were identified.

Conclusions:

  • Group-theoretical analysis offers a pathway to interpretable DNNs in scientific computing and DSP.
  • The method uncovers emergent, sophisticated functionalities within networks, validating their potential for complex signal processing tasks.
  • This approach significantly enhances the trustworthiness of DNNs for critical scientific applications.