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

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.9K
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...
11.9K
Types Of Transformers01:16

Types Of Transformers

1.0K
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
1.0K
The Ideal Transformer01:26

The Ideal Transformer

887
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
887
Energy Losses in Transformers01:21

Energy Losses in Transformers

969
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality,  the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be  the high resistance of the...
969
Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

205
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
205
Transformers in Distribution System01:27

Transformers in Distribution System

156
Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
156

You might also read

Related Articles

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

Sort by
Same author

Neural and computational correlates of strategic aborting and long-run policy optimization in the dorsolateral prefrontal cortex.

Nature communications·2026
Same author

The Metabolic Role of Mitochondria in the Perinatal Cardiac Development and Cardiovascular Diseases.

Exploration (Beijing, China)·2026
Same author

A tri-modal contrastive learning framework for protein representation learning.

Cell reports methods·2026
Same author

Functional specialisation of ammonium transporters in the ectomycorrhizal fungus Laccaria bicolor.

The New phytologist·2026
Same author

Evolutionary convergence and divergence of hippocampal cytoarchitecture between rodents and primates revealed by single-cell spatial transcriptomics.

National science review·2026
Same author

scLong: a billion-parameter foundation model for capturing long-range gene context in single-cell transcriptomics.

Nature communications·2026

Related Experiment Video

Updated: Sep 11, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681

Transformer Architecture Search for Improving Out-of-Domain Generalization in Machine Translation.

Yiheng He1, Ruiyi Zhang1, Sai Ashish Somayajula1

  • 1UC San Diego.

Transactions on Machine Learning Research
|August 18, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method for automatically finding Transformer neural architectures that perform well on machine translation (MT) tasks, even with out-of-domain (OOD) data. The approach enhances generalization by synthesizing OOD data during architecture search.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

491

Related Experiment Videos

Last Updated: Sep 11, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

491

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Artificial Intelligence

Background:

  • Automatic searching for Transformer neural architectures for machine translation (MT) is gaining traction.
  • Existing methods excel in in-domain scenarios but falter with out-of-domain (OOD) data, common in real-world applications.
  • Transformer architectures optimized for training data struggle with OOD test data due to distribution shifts.

Purpose of the Study:

  • To propose a multi-level optimization method for automatically searching neural architectures with robust OOD generalization capabilities.
  • To develop an integrated approach for synthesizing approximated OOD MT data and searching for optimal architectures simultaneously.
  • To improve the accuracy of machine translation in real-world scenarios with varying data distributions.

Main Methods:

  • A multi-level optimization framework is employed to search for Transformer architectures.
  • Approximated out-of-domain (OOD) machine translation data is synthesized during the architecture search process.
  • The synthesis of OOD data and architecture search are integrated into an end-to-end process for evaluating and enhancing generalization.

Main Results:

  • The proposed method demonstrates strong OOD generalization performance across multiple datasets.
  • The approach surpasses existing state-of-the-art methods in handling out-of-domain machine translation.
  • The synthesized OOD data effectively aids in improving the generalization capabilities of the searched architectures.

Conclusions:

  • The developed method offers a robust solution for automatically discovering Transformer architectures that generalize well to OOD machine translation.
  • Integrated OOD data synthesis and architecture search provide an effective strategy for tackling distribution shifts in MT.
  • The publicly available code facilitates further research and application of these OOD-robust architecture search techniques.