Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Algorithms  /  Vol: 12 Par: 8 (2019)  /  Artículo
ARTÍCULO
TITULO

Idea of Using Blockchain Technique for Choosing the Best Configuration of Weights in Neural Networks

Alicja Winnicka and Karolina Kesik    

Resumen

The blockchain technique is becoming more and more popular due to its advantages such as stability and dispersed nature. This is an idea based on blockchain activity paradigms. Another important field is machine learning, which is increasingly used in practice. Unfortunately, the training or overtraining artificial neural networks is very time-consuming and requires high computing power. In this paper, we proposed using a blockchain technique to train neural networks. This type of activity is important due to the possible search for initial weights in the network, which affect faster training, due to gradient decrease. We performed the tests with much heavier calculations to indicate that such an action is possible. However, this type of solution can also be used for less demanding calculations, i.e., only a few iterations of training and finding a better configuration of initial weights.

Palabras claves

 Artículos similares

       
 
Mamoon Riaz, Hammad Dilpazir, Sundus Naseer, Hasan Mahmood, Asim Anwar, Junaid Khan, Ian B. Benitez and Tanveer Ahmad    
In the past few decades, the transmission of data over an unsecure channel has resulted in an increased rate of hacking. The requirement to make multimedia data more secure is increasing day by day. Numerous algorithms have been developed to improve effi... ver más
Revista: Information

 
Saul G. Ramirez, Gustavious Paul Williams, Norman L. Jones, Daniel P. Ames and Jani Radebaugh    
Obtaining and managing groundwater data is difficult as it is common for time series datasets representing groundwater levels at wells to have large gaps of missing data. To address this issue, many methods have been developed to infill or impute the mis... ver más
Revista: Water

 
Minseok Kong and Jungmin So    
There are several automated stock trading programs using reinforcement learning, one of which is an ensemble strategy. The main idea of the ensemble strategy is to train DRL agents and make an ensemble with three different actor?critic algorithms: Advant... ver más
Revista: Applied Sciences

 
Kang Niu, Xu Bai, Xi Chen, Jianqiao Yu and Haiying Liu    
In the model (m:n), to improve the autonomous collaborative interception capability for air vehicle, a new autonomous cross-collaborative interception algorithm based on GTSMC (Global Terminal Sliding Mode Control) and real-time virtual geometry is propo... ver más
Revista: Aerospace

 
Oscar Scussel, Michael J. Brennan, Fabrício Cézar L. de Almeida, Mauricio K. Iwanaga, Jennifer M. Muggleton, Phillip F. Joseph and Yan Gao    
The frequency range of the leak noise in buried water pipes, measured using acoustic correlators, depends significantly on the type of pipe and its location as well as the type of sensors used. Having a rough idea of this frequency range can be beneficia... ver más
Revista: Acoustics