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

Improving Translational Accuracy

Improving Translational Accuracy

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...

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

Weighted Mean

Weighted Mean

While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...

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

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

Same author

Longitudinal multi-omics decipher chlorinated paraffin 52 disruption of gut-brain axis homeostasis in HFD-fed mice.

Ecotoxicology and environmental safety·2025

Same journal

Scaling Up Bayesian Neural Networks with Neural Networks.

Transactions on machine learning research·2026

Same journal

Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation.

Transactions on machine learning research·2026

Same journal

Still Competitive: Revisiting Recurrent Models for Irregular Time Series Prediction.

Transactions on machine learning research·2026

Same journal

Multi-Modal Foundation Models for Computational Pathology: A Survey.

Transactions on machine learning research·2026

Same journal

Sparse-Input Neural Network using Group Concave Regularization.

Transactions on machine learning research·2026

Same journal

Bayesian Neighborhood Adaptation for Graph Neural Networks.

Transactions on machine learning research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 10, 2025

Evaluating Skilled Prehension in Mice Using an Auto-Trainer

Evaluating Skilled Prehension in Mice Using an Auto-Trainer

Published on: September 12, 2019

TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining.

Ruiyi Zhang¹, Sai Ashish Somayajula¹, Pengtao Xie¹

¹UC San Diego.

Transactions on Machine Learning Research

|August 26, 2025

Summary

This summary is machine-generated.

This study introduces TapWeight, a novel framework for task-adaptive pretraining (TAP) that automatically optimizes objective importance using downstream feedback. TapWeight improves machine learning model performance across diverse tasks by efficiently adapting pretraining strategies.

More Related Videos

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

Published on: April 15, 2014

Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation

Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation

Published on: August 23, 2017

Related Experiment Videos

Last Updated: Sep 10, 2025

Evaluating Skilled Prehension in Mice Using an Auto-Trainer

Evaluating Skilled Prehension in Mice Using an Auto-Trainer

Published on: September 12, 2019

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

Published on: April 15, 2014

Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation

Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation

Published on: August 23, 2017

Area of Science:

Machine Learning
Artificial Intelligence
Computational Science

Background:

Large-scale pretraining followed by finetuning is standard in machine learning.
Domain discrepancies can hinder model performance, necessitating task-adaptive pretraining (TAP).
Existing TAP methods often manually tune objective tradeoffs, leading to inefficiencies.

Purpose of the Study:

To introduce TapWeight, a framework for automated task-adaptive pretraining.
To address the limitations of manual objective tradeoff determination in TAP.
To enhance model performance by dynamically adjusting pretraining objective importance.

Main Methods:

Developed TapWeight, a task-adaptive pretraining framework.
Implemented a multi-level optimization approach to automatically reweight pretraining objectives based on downstream feedback.
Applied the framework to molecular property prediction and natural language processing tasks.

Main Results:

TapWeight significantly outperformed baseline methods in both molecular property prediction and NLP tasks.
Experimental results demonstrated the effectiveness and generalizability of the TapWeight framework.
The automated objective weighting led to improved performance and potentially reduced computational costs.

Conclusions:

TapWeight offers an effective and generalizable solution for task-adaptive pretraining.
Automating the optimization of pretraining objectives enhances model performance.
The proposed method provides a more efficient approach to TAP compared to manual tuning.