Unsupervised Pre-training on Improving the Performance of Neural Network in Regression

机译：改善神经网络回归性能的无监督预训练

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

The paper aims to empirically analyse the performance of the prediction capability of Artificial Neural Network by applying a pre-training mechanism. The pre-training used here is same as the training of Deep Belief Network where the network is formed by stacking Restricted Boltzmann Machine one above the other successively. A different set of experiments are performed to understand in what scenario pre-trained ANN performed better than randomly initialised ANN. The results of experiments showed that pre-trained model performed better than randomly initialised ANN in terms of generalised error, computational units required and most importantly robust to change in hyperparameters such as learning rate and model architecture. The only cost is in additional time involved in the pre-training phase. Further, the learned knowledge in pretraining, which is stored as weights in ANN, are analysed using Hinton diagram. The analysis could provide clear picture of the pre-training that learned some of the hidden characteristics of the data.

机译：本文旨在通过应用一种预训练机制来对人工神经网络的预测能力的性能进行实证分析。这里使用的预训练与深度信任网络的训练相同，在深度信任网络中，网络是通过将限制性玻尔兹曼机一个接一个地堆叠而形成的。进行了不同的实验，以了解在什么情况下预训练的ANN比随机初始化的ANN更好。实验结果表明，在广义误差，所需的计算单位以及最重要的是在诸如学习率和模型体系结构等超参数变化方面，预训练模型的性能要优于随机初始化的ANN。唯一的成本是在预训练阶段要花费额外的时间。此外，使用欣顿图分析了在预训练中学到的知识，这些知识作为权重存储在ANN中。该分析可以清楚地了解学习数据的某些隐藏特征的预训练。

著录项

来源
《International Joint Conference on Neural Networks》|2018年|1-6|共6页
会议地点
作者
Pallabi Saikia; Prateek Vij; Rashmi Dutta Baruah;
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
Training; Analytical models; Predictive models; Data models; Biological neural networks; Neurons;

机译：培训;分析模型;预测模型;数据模型;生物神经网络;神经元;

相似文献

外文文献
中文文献
专利

1. Performance prediction of switched reluctance motor using improved generalized regression neural networks for design optimization [J] . Zhu Zhang, Shenghua Rao, Xiaoping Zhang CES Transactions on Electrical Machines and Systems . 2018,第4期

机译：使用改进的广义回归神经网络进行开关磁阻电机性能优化设计预测
2. Improving the generalization performance of RBF neural networks using a linear regression technique [J] . C.L Lin, J.F. Wang, C.Y. Chen, Expert systems with applications . 2009,第10期

机译：使用线性回归技术提高RBF神经网络的泛化性能
3. Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia [J] . NeuroImage . 2016,第Pta1期

机译：具有权重稀疏控制和预训练的深度神经网络可提取分层特征并增强分类性能：来自精神分裂症的全脑静止状态功能连接模式的证据
4. Unsupervised Pre-training on Improving the Performance of Neural Network in Regression [C] . Pallabi Saikia, Prateek Vij, Rashmi Dutta Baruah International Joint Conference on Neural Networks . 2018

机译：提高回归中神经网络性能的无监督培训
5. Comparing the performance of ordinal logistic regression and artificial neural network when analyzing ordinal data. [D] . Larasati, Aisyah. 2012

机译：分析顺序数据时比较顺序逻辑回归和人工神经网络的性能。
6. Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning [O] . Chankyu Lee, Priyadarshini Panda, Gopalakrishnan Srinivasan, 2018

机译：通过基于STDP的无监督预训练和有监督的微调来训练深度尖峰卷积神经网络
7. Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning [O] . Chankyu Lee, Priyadarshini Panda, Gopalakrishnan Srinivasan, 2018

机译：培养深度尖峰卷积神经网络，与基于STDP的无监督的预测预测，然后进行了监督微调

Unsupervised Pre-training on Improving the Performance of Neural Network in Regression

摘要

著录项

相似文献

相关主题

期刊订阅