REVISTA
AI

   
Redirigiendo al acceso original de articulo en 15 segundos...
Inicio  /  AI  /  Vol: 3 Par: 4 (2022)  /  Artículo
ARTÍCULO
TITULO

Model Soups for Various Training and Validation Data

Kaiyu Suzuki and Tomofumi Matsuzawa    

Resumen

Model soups synthesize multiple models after fine-tuning them with different hyperparameters based on the accuracy of the validation data. They train different models on the same training and validation data sets. In this study, we maximized the model fine-tuning accuracy using the inference time and memory cost of a single model. We extended the model soups to create subsets of k training and validation data using a method similar to k-fold cross-validation and trained models on these subsets. First, we showed the correlation between the validation and test data when the models are synthesized, such that their training data contain validation data. Thereafter, we showed that synthesizing k of these models, after synthesizing models based on subsets of the same training and validation data, provides a single model with high test accuracy. This study provides a method for learning models with both high accuracy and reliability for small datasets such as medical images.

 Artículos similares

       
 
Somayeh Shahrabadi, Telmo Adão, Emanuel Peres, Raul Morais, Luís G. Magalhães and Victor Alves    
The proliferation of classification-capable artificial intelligence (AI) across a wide range of domains (e.g., agriculture, construction, etc.) has been allowed to optimize and complement several tasks, typically operationalized by humans. The computatio... ver más
Revista: Algorithms

 
Kalyan Chatterjee, M. Raju, N. Selvamuthukumaran, M. Pramod, B. Krishna Kumar, Anjan Bandyopadhyay and Saurav Mallik    
According to global data on visual impairment from the World Health Organization in 2010, an estimated 285 million individuals, including 39 million who are blind, face visual impairments. These individuals use non-contact methods such as voice commands ... ver más
Revista: Information

 
Yong Liu, Xiaohui Yan, Wenying Du, Tianqi Zhang, Xiaopeng Bai and Ruichuan Nan    
The current work proposes a novel super-resolution convolutional transposed network (SRCTN) deep learning architecture for downscaling daily climatic variables. The algorithm was established based on a super-resolution convolutional neural network with t... ver más
Revista: Water

 
Sunny Kumar Poguluri and Yoon Hyeok Bae    
The incorporation of machine learning (ML) has yielded substantial benefits in detecting nonlinear patterns across a wide range of applications, including offshore engineering. Existing ML works, specifically supervised regression models, have not underg... ver más

 
Zeyu Xu, Wenbin Yu, Chengjun Zhang and Yadang Chen    
In the era of noisy intermediate-scale quantum (NISQ) computing, the synergistic collaboration between quantum and classical computing models has emerged as a promising solution for tackling complex computational challenges. Long short-term memory (LSTM)... ver más
Revista: Information