transfer learning
PulseAugur coverage of transfer learning — every cluster mentioning transfer learning across labs, papers, and developer communities, ranked by signal.
10 day(s) with sentiment data
-
AI framework boosts optical network reliability with guaranteed uncertainty bands
Researchers have developed a Conformal Risk Control (CRC) framework to enhance the reliability of AI/ML regression models used in optical networks. This post-hoc method provides statistically guaranteed uncertainty band…
-
Dissertation questions transfer learning generalization assumptions
A new dissertation explores the effectiveness of transfer learning in deep learning, questioning whether strong generalization on a source task guarantees transferability to a related target task. The research hypothesi…
-
AI models evaluated for IoT DDoS detection under resource constraints
A new research paper evaluates several pre-trained convolutional neural network architectures for detecting distributed denial-of-service (DDoS) attacks in resource-constrained Internet of Things (IoT) environments. The…
-
Deep learning enhances 4D Flow MRI for cerebrovascular imaging · 2 sources tracked
Researchers have developed a deep learning model that improves the resolution of 4D Flow MRI scans for cerebrovascular imaging. By utilizing synthetic pretraining and multi-cohort transfer learning, the convolutional ne…
-
New contrastive learning method optimizes representation geometry for imbalanced datasets
Researchers have developed a new theoretical framework to understand representation geometry in supervised contrastive learning, particularly for datasets with long-tailed distributions. Their analysis revealed that exi…
-
PYTHIA framework uses transfer learning for material optimization
Researchers have introduced PYTHIA, a novel machine learning framework designed to optimize material properties like defects and adsorption sites. PYTHIA leverages foundational models and transfer learning, utilizing a …
-
New transfer learning framework boosts VLC indoor localization accuracy
Researchers have developed a novel transfer learning framework to improve indoor localization accuracy in Visible Light Communication (VLC) systems, particularly for Industry 4.0 applications. This framework significant…
-
New algorithm optimizes action masking in reinforcement learning
Researchers have developed a new algorithm for reinforcement learning that addresses the computational bottleneck of determining permissible actions. This algorithm, based on deterministic optimistic optimization, is sh…
-
New transfer learning method achieves minimax-optimal scaling in regression
Researchers have developed a new method for transfer learning in high-dimensional regression, focusing on the performance improvements achievable through pretrained models. Their work establishes a deterministic equival…
-
AI model estimates petroleum well pressure, outperforming physical sensors
Researchers have developed a machine learning model to estimate bottom-hole pressure in petroleum wells, offering a cost-effective alternative to physical sensors. The study, which utilizes Long Short-Term Memory (LSTM)…
-
New generative model approach enhances conditional distribution equality testing
Researchers have developed a novel method for testing conditional distribution equality, a crucial problem in areas like causal inference and transfer learning. This new approach utilizes generative models to compare co…
-
New transfer learning model enhances building control performance
Researchers have developed a novel zero-shot transfer learning approach for model predictive control (MPC) in buildings. This method utilizes generalized models pretrained on excitation-based operational data, which pur…
-
New divergence-based similarity function enhances multi-view contrastive learning
Researchers have developed a new divergence-based similarity function (DSF) for multi-view contrastive learning, aiming to better capture the joint structure across multiple augmented data views. Unlike previous methods…
-
Transfer learning enhances models for electron-nucleus cross sections
Researchers have developed data-driven models for electron-nucleus cross sections using transfer learning. These models, initially trained on carbon data, were fine-tuned for various other elements including helium, lit…
-
Deep learning model classifies galaxy morphology using crowd-sourced data
Researchers have adapted a deep neural network, specifically a convolutional neural network (CNN), for the morphological classification of galaxies using crowd-sourced annotations from the Galaxy Zoo 1 dataset. The stud…
-
New multi-task learning model predicts grape cold hardiness
Researchers have developed multi-task learning (MTL) approaches using recurrent neural networks (RNNs) to predict grape cold hardiness from time series weather data. This method addresses the challenge of sparse and lim…
-
Transfer Learning: Leveraging Pretrained Models for New Tasks
This article explains the concept of transfer learning, a technique in machine learning where a model trained on one task is repurposed for a second related task. It highlights how using a pre-trained neural network can…
-
AI Concepts Explained: A Guide to Modern AI
This article provides a jargon-free explanation of 15 core concepts that underpin modern artificial intelligence. It covers fundamental areas such as machine learning, deep learning, neural networks, and natural languag…
-
New Sobolev Regularized Score Difference Estimator for Diffusion Models
Researchers have developed a new method for estimating score differences in diffusion models, crucial for tasks like transfer learning and post-training adjustments. This Sobolev regularized score difference estimator o…
-
Transfer learning and AI show promise for Alzheimer's diagnosis
A new review paper explores the application of transfer learning (TL) techniques in diagnosing Alzheimer's disease (AD) using neuroimaging data. The paper highlights how TL can improve diagnostic accuracy, especially wh…