Jove
Visualize
Contact Us

Related Concept Videos

Transfer Function to State Space01:23

Transfer Function to State Space

512
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 RLC...
512
State Space to Transfer Function01:21

State Space to Transfer Function

376
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:
376
Associative Learning01:27

Associative Learning

788
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
788
Improving Translational Accuracy02:07

Improving Translational Accuracy

12.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.2K
3.2K
Convolution Properties I01:20

Convolution Properties I

318
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
318

You might also read

Related Articles

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

Sort by
Same author

Systems Policy Analysis for Antimicrobial Resistance Targeted Action (SPAARTA): A Research Protocol.

Wellcome open research·2025
Same author

Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge.

Nature communications·2025
Same author

Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study.

JMIR medical informatics·2025
Same author

Development of an explainable artificial intelligence model for Asian vascular wound images.

International wound journal·2023
Same author

Artificial intelligence education for radiographers, an evaluation of a UK postgraduate educational intervention using participatory action research: a pilot study.

Insights into imaging·2023
Same author

Enhancing MR image segmentation with realistic adversarial data augmentation.

Medical image analysis·2022
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 Experiment Video

Updated: Nov 4, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.7K

Anti-transfer learning for task invariance in convolutional neural networks for speech processing.

Eric Guizzo1, Tillman Weyde1, Giacomo Tarroni1

  • 1Department of Computer Science City, University of London, United Kingdom.

Neural Networks : the Official Journal of the International Neural Network Society
|May 25, 2021
PubMed
Summary

Anti-transfer learning prevents models from learning irrelevant information from orthogonal tasks, improving speech processing accuracy. This method enhances generalization and controls unwanted correlations, making models more robust and unbiased.

Keywords:
Audio processingConvolutional neural networksInvariance transferTransfer learning

More Related Videos

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback
05:43

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback

Published on: May 23, 2019

5.6K

Related Experiment Videos

Last Updated: Nov 4, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.7K
Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback
05:43

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback

Published on: May 23, 2019

5.6K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Speech Processing

Background:

  • Transfer learning leverages pre-trained models for new tasks.
  • Orthogonal tasks, irrelevant or confounding to the target task, can negatively impact transfer learning.
  • Pre-trained models are increasingly available, offering potential for broader applications.

Purpose of the Study:

  • Introduce anti-transfer learning to prevent learning from orthogonal tasks in speech processing.
  • Develop a method to improve model generalization and control spurious correlations.
  • Enhance the utility of pre-trained models by ensuring task-relevant feature extraction.

Main Methods:

  • Implemented anti-transfer learning for convolutional neural networks.
  • Penalized similarity between network activations from target and orthogonal tasks.
  • Evaluated various configurations, similarity metrics, and aggregation functions across multiple datasets.

Main Results:

  • Anti-transfer learning achieved desired invariance to orthogonal tasks.
  • Resulted in more appropriate features for the target speech processing tasks.
  • Consistently improved classification accuracy across all evaluated scenarios.

Conclusions:

  • Anti-transfer learning offers a novel approach to enhance model performance and control feature relevance.
  • It is widely applicable, especially when specific invariances are needed or labeled data for orthogonal tasks are scarce.
  • While incurring some training costs, it offers significant benefits for model generalization and accuracy.