A novel optimized GA–Elman neural network algorithm

Jia, Weikuan; Zhao, Debin; Zheng, Yuanjie; Hou, Sujuan

doi:10.1007/s00521-017-3076-7

Cited by 57 publications

(20 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, we chose the Elman neural network to build the model. The Elman neural network structure is shown in Figure 1: The Elman neural network consists of four layers, which are input layer, hidden layer, context layer and output layer [11]. The input layer transmits external signals to the hidden layer.…”

Section: Elman Neural Network (Enn)mentioning

confidence: 99%

A Short-Term Forecast Model of foF2 Based on Elman Neural Network

et al. 2019

View full text Add to dashboard Cite

The critical frequency foF2 of the ionosphere F2 layer is one of the most important parameters of the ionosphere. Based on the Elman neural network (ENN), this paper constructs a single station forecasting model to predict foF2 one hour ahead. In order to avoid the network falling into local minimum, the model is optimized by the improved particle swarm optimization (IPSO). The input parameters used in the model include local time, seasonal information, solar cycle information and magnetic activity information. Data of the Wuhan Station from 2008 to 2016 were used to train and test the model. The prediction results of foF2 show that the root mean square error (RMSE) of the Elman neural network model is 4.30% lower than that of the back-propagation neural network (BPNN) model. The RMSE is further reduced by 8.92% after using the IPSO to optimize the model. This indicates that the Elman neural network model optimized by the improved particle swarm optimization is superior to the BP neural network and Elman neural network in the forecast of foF2 one hour ahead at Wuhan station.

show abstract

Section: Elman Neural Network (Enn)mentioning

confidence: 99%

A Short-Term Forecast Model of foF2 Based on Elman Neural Network

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Elman neural network has been widely used in many fields. 34,35 However, Elman neural network carries forward the advantages of the back-propagation (BP) algorithm and, at the same time, it also inevitably inherited the some inherent disadvantages of the BP network, such as easy to trap in local minimum, resulting in training failure; the learning rate is fixed, which limits the network's convergence rate; the number of hidden neurons is difficult to determine, thus artificial attempts to waste a lot of time. These deficiencies limit the neural network transport efficiency and recognition accuracy.…”

Section: Thought Of Ga-elman Algorithmmentioning

confidence: 99%

Fruit recognition based on pulse coupled neural network and genetic Elman algorithm application in apple harvesting robot

Jia

Mou

Wang

et al. 2020

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

In order to improve the harvesting efficiency of apple harvesting robot, this article presents an apple recognition method based on pulse coupled neural network and genetic Elman neural network (GA-Elman). Firstly, we use pulse coupled neural network to segment the captured 150 images, respectively, and extract six color features of R, G, B, H, S, and I and 10 shape features of circular variance, density, the ratio of perimeter square to area, and Hu invariant moments of segmented images, and these 16 features are considered as the inputs of Elman neural network. In order to overcome some defects of Elman neural network, such as, trapping local minimum easily and determining the number of hidden neurons difficultly; in this article, genetic algorithm is introduced to optimize it, and new optimization way is designed, that is, the connection weights and number of hidden neurons separate encoding and evolving simultaneously, in the process of structural evolution at the same time the learning of connection weights is completed, and then the operating efficiency and recognition precision of Elman model are improved. In order to get more precision neural network, and avoid the influence of fruit recognition caused by branches or leaves shadow, apple along with branches and leaves is allowed to train. The results of experiments show that compared with the traditional back-propagation, Elman neural network, and other two recognition algorithms of obscured fruit. the genetic Elman neural network algorithm is the optimal method which successful training rate can reach to 100%, recognition rate of overlapping fruit and obscured fruit can reach to 88.67% and 93.64%, respectively, and the total recognition rate reaches to 94.88%.

show abstract

“…Their work is tested on LSTMs using image captioning, speech recognition, and language processing applications showing a speedup of 5.1, 44.9 and 1.53, respectively. Recently, GA is introduced into the Elman architecture to accelerate the training and prevent the local minima problem [18]. GA-Elman outperformes traditional training algorithms in terms of convergence speed and accuracy.…”

Section: Parallelizing Iterative Training Algorithms For Rnnmentioning

confidence: 99%

An Optimized Parallel Implementation of Non-Iteratively Trained Recurrent Neural Networks

Zini

Rizk

Awad

2020

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length of the time dependencies and the number of hidden neurons increase. To reduce the training time, extreme learning machines (ELMs) have been recently applied to RNN training, reaching a 99% speedup on some applications. Due to its non-iterative nature, ELM training, when parallelized, has the potential to reach higher speedups than BPTT.In this work, we present Opt-PR-ELM, an optimized parallel RNN training algorithm based on ELM that takes advantage of the GPU shared memory and of parallel QR factorization algorithms to efficiently reach optimal solutions. The theoretical analysis of the proposed algorithm is presented on six RNN architectures, including LSTM and GRU, and its performance is empirically tested on ten time-series prediction applications. Opt-PR-ELM is shown to reach up to 461 times speedup over its sequential counterpart and to require up to 20x less time to train than parallel BPTT. Such high speedups over new generation CPUs are extremely crucial in real-time applications and IoT environments.

show abstract

A novel optimized GA–Elman neural network algorithm

Cited by 57 publications

References 21 publications

A Short-Term Forecast Model of foF2 Based on Elman Neural Network

A Short-Term Forecast Model of foF2 Based on Elman Neural Network

Fruit recognition based on pulse coupled neural network and genetic Elman algorithm application in apple harvesting robot

An Optimized Parallel Implementation of Non-Iteratively Trained Recurrent Neural Networks

Contact Info

Product

Resources

About