Segment, Perceive and Classify - Multitask Learning of the Electrocardiogram in a Single Neural Network

2021 ◽  
Author(s):  
Philipp F Sodmann ◽  
Marcus Vollmer ◽  
Lars Kaderali
Keyword(s):  
Neural Network ◽  
Multitask Learning ◽  
Single Neural Network

scholarly journals A DBN-Based Deep Neural Network Model with Multitask Learning for Online Air Quality Prediction

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Jiangeng Li ◽  
Xingyang Shao ◽  
Rihui Sun
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Network Model ◽  
Neural Network Model ◽  
Prediction Accuracy ◽  
Deep Neural Network ◽  
Multitask Learning ◽  
Air Pollutant ◽  
Quality Prediction ◽  
Air Quality Prediction

To avoid the adverse effects of severe air pollution on human health, we need accurate real-time air quality prediction. In this paper, for the purpose of improve prediction accuracy of air pollutant concentration, a deep neural network model with multitask learning (MTL-DBN-DNN), pretrained by a deep belief network (DBN), is proposed for forecasting of nonlinear systems and tested on the forecast of air quality time series. MTL-DBN-DNN model can solve several related prediction tasks at the same time by using shared information contained in the training data of different tasks. In the model, DBN is used to learn feature representations. Each unit in the output layer is connected to only a subset of units in the last hidden layer of DBN. Such connection effectively avoids the problem that fully connected networks need to juggle the learning of each task while being trained, so that the trained networks cannot get optimal prediction accuracy for each task. The sliding window is used to take the recent data to dynamically adjust the parameters of the MTL-DBN-DNN model. The MTL-DBN-DNN model is evaluated with a dataset from Microsoft Research. Comparison with multiple baseline models shows that the proposed MTL-DBN-DNN achieve state-of-art performance on air pollutant concentration forecasting.

Estimation of Polypropylene Melt Index through the Application of Stacked Neural Networks

2011 ◽  
Vol 187 ◽  
pp. 411-415
Author(s):  
Lu Yue Xia ◽  
Hai Tian Pan ◽  
Meng Fei Zhou ◽  
Yi Jun Cai ◽  
Xiao Fang Sun
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Model ◽  
Neural Network Model ◽  
Model Performance ◽  
Measurement Interval ◽  
Melt Index ◽  
Polypropylene Melt ◽  
Single Neural Network

Melt index is the most important parameter in determining the polypropylene grade. Since the lack of proper on-line instruments, its measurement interval and delay are both very long. This makes the quality control quite difficult. A modeling approach based on stacked neural networks is proposed to estimation the polypropylene melt index. Single neural network model generalization capability can be significantly improved by using stacked neural networks model. Proper determination of the stacking weights is essential for good stacked neural networks model performance, so determination of appropriate weights for combining individual networks using the criteria about minimization of sum of absolute prediction error is proposed. Application to real industrial data demonstrates that the polypropylene melt index can be successfully estimated using stacked neural networks. The results obtained demonstrate significant improvements in model accuracy, as a result of using stacked neural networks model, compared to using single neural network model.

scholarly journals Stereo Matching Based on Immune Neural Network in Abdomen Reconstruction

2015 ◽  
Vol 2015 ◽  
pp. 1-15
Author(s):  
Huan Liu ◽  
Kuangrong Hao ◽  
Yongsheng Ding ◽  
Chunjuan Ouyang
Keyword(s):  
Neural Network ◽  
Stereo Matching ◽  
Feature Matching ◽  
Three Dimensional ◽  
Target Point ◽  
Feature Points ◽  
Matching Algorithm ◽  
Optimization Task ◽  
Feasible Alternative ◽  
Single Neural Network

Stereo feature matching is a technique that finds an optimal match in two images from the same entity in the three-dimensional world. The stereo correspondence problem is formulated as an optimization task where an energy function, which represents the constraints on the solution, is to be minimized. A novel intelligent biological network (Bio-Net), which involves the human B-T cells immune system into neural network, is proposed in this study in order to learn the robust relationship between the input feature points and the output matched points. A model from input-output data (left reference point-right target point) is established. In the experiments, the abdomen reconstructions for different-shape mannequins are then performed by means of the proposed method. The final results are compared and analyzed, which demonstrate that the proposed approach greatly outperforms the single neural network and the conventional matching algorithm in precise. Particularly, as far as time cost and efficiency, the proposed method exhibits its significant promising and potential for improvement. Hence, it is entirely considered as an effective and feasible alternative option for stereo matching.

Multitask Similarity Cluster

2013 ◽  
Vol 765-767 ◽  
pp. 1662-1666
Author(s):  
Zhen Xing Li ◽  
Wei Hua Li
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Satisfactory Result ◽  
Hellinger Distance ◽  
Multitask Learning ◽  
Experimental Results ◽  
Improve Performance ◽  
Single Task ◽  
Artificial Neural ◽  
Learning Machine

Single task learning is widely used training in artificial neural network. Before, people usually see other tasks as noise in same learning machine. However, multitask learning, proposed by Rich Caruana, sees simultaneously training several correlated tasks is helpful to improve single tasks performance. In this paper, we propose a new neural network multitask similarity cluster. Combined with hellinger distance, multitask similarity cluster can estimate distances among clusters more accurate. Experimental results show multitask learning is helpful to improve performance of single task and multitask similarity cluster can get satisfactory result.

Short-Term Gas Load Forecasting Based on Wavelet BP Neural Network Optimized by Genetic Algorithm

2014 ◽  
Vol 631-632 ◽  
pp. 79-85 ◽  
Author(s):  
Feng Yu ◽  
Zhi Qing Wang ◽  
Xiao Zhong Xu
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Bp Neural Network ◽  
Load Forecasting ◽  
Learning Ability ◽  
Time Frequency ◽  
Proposed Model ◽  
Real Coded Genetic Algorithm ◽  
Self Learning ◽  
Single Neural Network

Aiming at the limitations of a single neural network for effective gas load forecasting, a combinational model based on wavelet BP neural network optimized by genetic algorithm is proposed. The problems that traditional BP algorithm converges slowly and easily falls into local minimum are overcame. The wavelet neural network strengthens the function approximation capacity of the network by combining the well time-frequency local feature of wavelet transform with the self-learning ability of neural network. And optimized by the real coded genetic algorithm, the network converges more quick than non-optimized one. This proposed model is applied to daily gas load forecasting for Shanghai and the simulation results indicate that this algorithm has excellent prediction effect.

scholarly journals An individual claims reserving model for reported claims

2021 ◽  
Author(s):  
Andrea Gabrielli
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Cash Flows ◽  
Data Sets ◽  
Proof Of Concept ◽  
The Neural Network ◽  
Insurance Data ◽  
Future Cash Flows ◽  
Single Neural Network

AbstractWe present a claims reserving technique that uses claim-specific feature and past payment information in order to estimate claims reserves for individual reported claims. We design one single neural network allowing us to estimate expected future cash flows for every individual reported claim. We introduce a consistent way of using dropout layers in order to fit the neural network to the incomplete time series of past individual claims payments. A proof of concept is provided by applying this model to synthetic as well as real insurance data sets for which the true outstanding payments for reported claims are known.

Sign in / Sign up

Export Citation Format

Share Document