scholarly journals Research and Application of Improved AGP Algorithm for Structural Optimization Based on Feedforward Neural Networks

2015 ◽  
Vol 2015 ◽  
pp. 1-6
Author(s):  
Ruliang Wang ◽  
Huanlong Sun ◽  
Benbo Zha ◽  
Lei Wang
Keyword(s):  
Neural Networks ◽  
Structural Optimization ◽  
Network Performance ◽  
Feedforward Neural Networks ◽  
Improved Method ◽  
Pruning Algorithm ◽  
Network Pruning ◽  
Internal Relation ◽  
Traffic Capacity ◽  
Simulation Results

The adaptive growing and pruning algorithm (AGP) has been improved, and the network pruning is based on the sigmoidal activation value of the node and all the weights of its outgoing connections. The nodes are pruned directly, but those nodes that have internal relation are not removed. The network growing is based on the idea of variance. We directly copy those nodes with high correlation. An improved AGP algorithm (IAGP) is proposed. And it improves the network performance and efficiency. The simulation results show that, compared with the AGP algorithm, the improved method (IAGP) can quickly and accurately predict traffic capacity.

scholarly journals Implementation of Preisach-Krasnoselskii Hysteresis Model with the Use of Artificial Neural Networks

2021 ◽  
Author(s):  
Zhao Wang
Keyword(s):  
Neural Networks ◽  
Magnetic Hysteresis ◽  
Feedforward Neural Networks ◽  
Hysteresis Model ◽  
Electromagnetic Devices ◽  
Hysteresis Modeling ◽  
Simulation Results ◽  
And Performance ◽  
Hysteresis Phenomena ◽  
Double Integrals

Accurate modeling of hysteresis is essential for both the design and performance evaluation of electromagnetic devices. This project proposes the use of feedforward meural networks to implement an accurate magnetic hysteresis model based on the mathematical difinition provided by the Preisach-Krasnoselskii (P-K) model. Feedforward neural networks are a linear association networks that relate the ouput patterns to input patterns. By introducing the multi-layer feedforward neural networks make the hysteresis modeling accurate without estimation of double integrals. Simulation results provide the detailed illustrations. The comparisons with the experiments show that the proposed approach is able to satisfactorily reproduce many features of obsereved hysteresis phenomena an in turn can be used for many applications of interest.

Performance of Multi-Layer Feedforward Neural Networks to Predict Liver Transplantation Outcome

1996 ◽  
Vol 35 (01) ◽  
pp. 12-18 ◽  
Author(s):  
M. Subotin ◽  
W. Marsh ◽  
J. McMichael ◽  
J. J. Fung ◽  
I. Dvorchik
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Liver Transplantation ◽  
Missing Data ◽  
Network Performance ◽  
Missing Values ◽  
Feedforward Neural Networks ◽  
Linear Scaling ◽  
Data Set ◽  
New Approach

AbstractA novel multisolutional clustering and quantization (MCO) algorithm has been developed that provides a flexible way to preprocess data. It was tested whether it would impact the neural network’s performance favorably and whether the employment of the proposed algorithm would enable neural networks to handle missing data. This was assessed by comparing the performance of neural networks using a well-documented data set to predict outcome following liver transplantation. This new approach to data preprocessing leads to a statistically significant improvement in network performance when compared to simple linear scaling. The obtained results also showed that coding missing data as zeroes in combination with the MCO algorithm, leads to a significant improvement in neural network performance on a data set containing missing values in 59.4% of cases when compared to replacement of missing values with either series means or medians.

scholarly journals Small Network for Lightweight Task in Computer Vision: A Pruning Method Based on Feature Representation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Yisu Ge ◽  
Shufang Lu ◽  
Fei Gao
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Feature Representation ◽  
Fine Tuning ◽  
Practical Application ◽  
Pruning Algorithm ◽  
Network Pruning ◽  
Pruning Strategy ◽  
Speed Up ◽  
Network Compression

Many current convolutional neural networks are hard to meet the practical application requirement because of the enormous network parameters. For accelerating the inference speed of networks, more and more attention has been paid to network compression. Network pruning is one of the most efficient and simplest ways to compress and speed up the networks. In this paper, a pruning algorithm for the lightweight task is proposed, and a pruning strategy based on feature representation is investigated. Different from other pruning approaches, the proposed strategy is guided by the practical task and eliminates the irrelevant filters in the network. After pruning, the network is compacted to a smaller size and is easy to recover accuracy with fine-tuning. The performance of the proposed pruning algorithm is validated on the acknowledged image datasets, and the experimental results prove that the proposed algorithm is more suitable to prune the irrelevant filters for the fine-tuning dataset.

scholarly journals Implementation of Preisach-Krasnoselskii Hysteresis Model with the Use of Artificial Neural Networks

2021 ◽  
Author(s):  
Zhao Wang
Keyword(s):  
Neural Networks ◽  
Magnetic Hysteresis ◽  
Feedforward Neural Networks ◽  
Hysteresis Model ◽  
Electromagnetic Devices ◽  
Hysteresis Modeling ◽  
Simulation Results ◽  
And Performance ◽  
Hysteresis Phenomena ◽  
Double Integrals

Accurate modeling of hysteresis is essential for both the design and performance evaluation of electromagnetic devices. This project proposes the use of feedforward meural networks to implement an accurate magnetic hysteresis model based on the mathematical difinition provided by the Preisach-Krasnoselskii (P-K) model. Feedforward neural networks are a linear association networks that relate the ouput patterns to input patterns. By introducing the multi-layer feedforward neural networks make the hysteresis modeling accurate without estimation of double integrals. Simulation results provide the detailed illustrations. The comparisons with the experiments show that the proposed approach is able to satisfactorily reproduce many features of obsereved hysteresis phenomena an in turn can be used for many applications of interest.

scholarly journals An iterative pruning algorithm for feedforward neural networks

1997 ◽  
Vol 8 (3) ◽  
pp. 519-531 ◽  
Author(s):  
G. Castellano ◽  
A.M. Fanelli ◽  
M. Pelillo
Keyword(s):  
Neural Networks ◽  
Feedforward Neural Networks ◽  
Pruning Algorithm

Prediction of molecular-dynamics simulation results using feedforward neural networks: Reaction of a C2 dimer with an activated diamond (100) surface

2005 ◽  
Vol 123 (22) ◽  
pp. 224711 ◽  
Author(s):  
Paras M. Agrawal ◽  
Abdul N. A. Samadh ◽  
Lionel M. Raff ◽  
Martin T. Hagan ◽  
Satish T. Bukkapatnam ◽  
...  
Keyword(s):  
Neural Networks ◽  
Molecular Dynamics ◽  
Molecular Dynamics Simulation ◽  
Feedforward Neural Networks ◽  
Dynamics Simulation ◽  
Simulation Results
Sign in / Sign up

Export Citation Format

Share Document