Recurrent neural network from adder’s perspective: Carry-lookahead RNN

Jiang, Haowei; Qin, Feiwei; Jin, Cao; Peng, Yong; Shao, Yanli

doi:10.1016/j.neunet.2021.08.032

Cited by 32 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, the genetic algorithm can help to adjust the connection weights and bias terms between the layers in the BP neural network, which enables the neural network to achieve a better fit on the training dataset and a better generalisation ability [12]. This combined optimisation approach tends to be more effective than using BP neural networks alone when dealing with complex problems [13].…”

Section: Genetic Algorithm Improved Bp Neural Network Modelmentioning

confidence: 99%

Prediction of Car Purchase Amount Based on Genetic Algorithm Optimised BP Neural Network Regression Algorithm

Chen,

Xu,

Wang

2024

Preprint

View full text Add to dashboard Cite

This study is based on the BP neural network regression model optimised by genetic algorithm and dedicated to predicting the amount of car purchase, this study is important for all parties in the automotive industry. By plotting the violins of six indicators, including gender, age, annual salary, credit card debt, net worth, and car purchase amount, we found that, except for gender, the other data showed a trend of dense in the middle gradually decreasing to the upper and lower sides, with an overall normal distribution. The correlation analysis shows that the amount of car purchase has a high positive correlation with age (0.63), followed by annual income (0.62), the correlation between net worth and the amount of car purchase is 0.49, while the correlation between credit card debt and the amount of car purchase is low (0.03). In the experimental part, we analyse the predicted-actual values of the training and test sets in comparison and find that the model predicted values are very close to the actual values. The RMSE of the training set is 11.559 and the RMSE of the test set is 11.4835, which is not much different from each other, indicating that the model has good generalisation ability. In addition, the R2 of both the training and test sets is 1, indicating that the model fits well. The MAE of the training set is 8.2512 and the MAE of the test set is 9.578; the MBE of the training set is -4.3035 and the MBE of the test set is -2.4547.These metrics indicate that the model performs well in predicting the amount of car purchase. In conclusion, this study provides an effective and reliable method to predict the amount of car purchase, creating a useful bridge between car manufacturers, dealers and consumers.

show abstract

Section: Genetic Algorithm Improved Bp Neural Network Modelmentioning

confidence: 99%

Prediction of Car Purchase Amount Based on Genetic Algorithm Optimised BP Neural Network Regression Algorithm

Chen,

Xu,

Wang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Lin and Cao (2020) [9] introduce a touch interactive system designed around an intelligent vase for psychotherapy tailored to Alzheimer's disease patients. Published in Designs, their work explores innovative approaches to integrating technology and therapeutic practices for enhancing patient engagement and wellbeing in Alzheimer's care.…”

Section: Liu Et Al (2024)mentioning

confidence: 99%

Exploring the Challenges and Future Directions of Big Data and AI in Education

Elam

2024

JAIGS

View full text Add to dashboard Cite

The integration of Big Data and Artificial Intelligence (AI) in education holds transformative potential, promising enhanced personalized learning experiences, improved administrative efficiency, and advanced predictive analytics. However, the adoption of these technologies also presents significant challenges. This paper explores the current landscape of Big Data and AI in education, identifying key challenges such as data privacy concerns, the digital divide, the need for teacher training, and the integration of AI with existing educational frameworks. Additionally, it examines potential future directions, including the development of ethical guidelines, advancements in adaptive learning technologies, and the creation of more inclusive and equitable AI systems. By addressing these challenges and leveraging future opportunities, the educational sector can harness the full potential of Big Data and AI to improve learning outcomes and operational efficiencies.

show abstract

“…The adder works similarly to RNNs [36]. Combined with the features of the adder, Carry-lookahead (CL-RNNs) is proposed in [37], which alleviates the problems in time series for parallel computing, thus mitigating the effects of the training complexity. However, the performance of CL-RNN in time series tasks is inferior to LSTM and GRU.…”

Section: Modified Rnnsmentioning

confidence: 99%

An Improved Time Feedforward Connections Recurrent Neural Networks

Wang¹,

Zou²,

Lim³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Recurrent Neural Networks (RNNs) have been widely applied to deal with temporal problems, such as flood forecasting and financial data processing. On the one hand, traditional RNNs models amplify the gradient issue due to the strict time serial dependency, making it difficult to realize a long-term memory function. On the other hand, RNNs cells are highly complex, which will significantly increase computational complexity and cause waste of computational resources during model training. In this paper, an improved Time Feedforward Connections Recurrent Neural Networks (TFC-RNNs) model was first proposed to address the gradient issue. A parallel branch was introduced for the hidden state at time t − 2 to be directly transferred to time t without the nonlinear transformation at time t − 1. This is effective in improving the long-term dependence of RNNs. Then, a novel cell structure named Single Gate Recurrent Unit (SGRU) was presented. This cell structure can reduce the number of parameters for RNNs cell, consequently reducing the computational complexity. Next, applying SGRU to TFC-RNNs as a new TFC-SGRU model solves the above two difficulties. Finally, the performance of our proposed TFC-SGRU was verified through several experiments in terms of long-term memory and anti-interference capabilities. Experimental results demonstrated that our proposed TFC-SGRU model can capture helpful information with time step 1500 and effectively filter out the noise. The TFC-SGRU model accuracy is better than the LSTM and GRU models regarding language processing ability.

show abstract

Recurrent neural network from adder’s perspective: Carry-lookahead RNN

Cited by 32 publications

References 17 publications

Prediction of Car Purchase Amount Based on Genetic Algorithm Optimised BP Neural Network Regression Algorithm

Prediction of Car Purchase Amount Based on Genetic Algorithm Optimised BP Neural Network Regression Algorithm

Exploring the Challenges and Future Directions of Big Data and AI in Education

An Improved Time Feedforward Connections Recurrent Neural Networks

Contact Info

Product

Resources

About