Training Optimization of Feedforward Neural Network for Binary Classification

机译：二元分类前馈神经网络的训练优化

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper, we present a heuristic based technique to reduce the training time of a feedforward neural network by intuiting some of the parameters involved in construction and initialization of the network. These estimated parameters include the number and size of the hidden layers along with the weights related to the neurons. The weights and network architecture is estimated before training by formulating a geometric approximation of the target function we want the network to learn. This specific configuration will allow the network to learn the optimum weights in less iterations than in the case of random initialization of weights.

机译：在本文中，我们提出一种基于启发式的技术，通过直观了解一些参与网络构建和初始化的参数来减少前馈神经网络的训练时间。这些估计的参数包括隐藏层的数量和大小以及与神经元有关的权重。权重和网络架构是在训练之前通过制定我们希望网络学习的目标函数的几何近似值来估计的。与权重的随机初始化的情况相比，这种特定的配置将允许网络以更少的迭代来学习最佳权重。

著录项

来源
《International Conference on Computer Communication and Informatics》|2019年|1-9|共9页
会议地点
作者
Omkar Thawakar; Pranav Gajjewar;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Neurons; Training; Task analysis; Optimization; Biological neural networks; Informatics; Feedforward neural networks;

机译：神经元;训练;任务分析;优化;生物神经网络;信息学;前馈神经网络;

相似文献

外文文献
中文文献
专利

1. Training feedforward neural networks using multi-verse optimizer for binary classification problems [J] . Faris Hossam, Aljarah Ibrahim, Mirjalili Seyedali Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies . 2016,第2期

机译：使用多节优化器训练前馈神经网络以解决二进制分类问题
2. A training algorithm for binary feedforward neural networks [J] . Gray D.L., Michel A.N. IEEE Transactions on Neural Networks . 1992,第2期

机译：二进制前馈神经网络的训练算法
3. Training binary node feedforward neural networks by back propagation of error [J] . Toms D.J. Electronics Letters . 1990,第21期

机译：通过误差的反向传播训练二元节点前馈神经网络
4. Training Optimization of Feedforward Neural Network for Binary Classification [C] . Omkar Thawakar, Pranav Gajjewar International Conference on Computer Communication and Informatics . 2019

机译：二进制分类馈电神经网络训练优化
5. Improving on-line training capacity of multilayer feedforward perceptron network for process control and optimization. [D] . Soleymani Yazdi, Mohammad R. 2003

机译：提高多层前馈感知器网络的在线培训能力，以进行过程控制和优化。
6. Training of feedforward neural networks for data classification using hybrid particle swarm optimization Mantegna Lévy flight and neighborhood search [O] . Omid Tarkhaneh, Haifeng Shen 2019

机译：使用混合粒子群优化MantegnaLévy飞行和邻域搜索训练前馈神经网络进行数据分类
7. Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search [O] . Omid Tarkhaneh, Haifeng Shen 2019

机译：使用混合粒子群优化，MantegnaLévy航班和邻里搜索训练用于数据分类的前馈神经网络。

Training Optimization of Feedforward Neural Network for Binary Classification

摘要

著录项

相似文献

相关主题

期刊订阅