MLPNN Training via a Multiobjective Optimization of Training Error and Stochastic Sensitivity

Yeung, Daniel; Li, Jincheng; Ng, Wing W. Y.; Chan, Patrick P. K.

doi:10.1109/tnnls.2015.2431251

Cited by 64 publications

(28 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimizing MLP for learning is based on selecting the suitable architecture and the connection weights via the minimizing training error and a penalty term [13]. Many techniques have been proposed to extend MLP abilities by additional components.…”

Section: Related Workmentioning

confidence: 99%

Effect of Additive Noise for Multi-Layered Perceptron with AutoEncoders

Sabri

Kurita

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper investigates the effect of noises added to hidden units of AutoEncoders linked to multilayer perceptrons. It is shown that internal representation of learned features emerges and sparsity of hidden units increases when independent Gaussian noises are added to inputs of hidden units during the deep network training. It is also shown that the weights that connect the contaminated hidden units with the next layer have smaller values and outputs of hidden units tend to be more definite (0 or 1). This is expected to improve the generalization ability of the network through this automatic structuration by adding the noises. This network structuration was confirmed by experiments for MNIST digits classification via a deep neural network model.

show abstract

Section: Related Workmentioning

confidence: 99%

Effect of Additive Noise for Multi-Layered Perceptron with AutoEncoders

Sabri

Kurita

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Therefore, we use a training method based on LGE to train the AE, referred to as LiSSA [45]. The goal of the LGE-based training method is to achieve a low generalization error for future unseen samples [46]. For machine-learning tasks, those unseen samples are usually near the training samples and do not exceed a distance Q, otherwise this training sample is not representative of the given problem.…”

Section: Localized Stochastic-sensitive Autoencoder (Lissa)mentioning

confidence: 99%

Radial Basis Function Neural Network with Localized Stochastic-Sensitive Autoencoder for Home-Based Activity Recognition

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Over the past few years, the Internet of Things (IoT) has been greatly developed with one instance being smart home devices gradually entering into people's lives. To maximize the impact of such deployments, home-based activity recognition is required to initially recognize behaviors within smart home environments and to use this information to provide better health and social care services. Activity recognition has the ability to recognize people's activities from the information about their interaction with the environment collected by sensors embedded within the home. In this paper, binary data collected by anonymous binary sensors such as pressure sensors, contact sensors, passive infrared sensors etc. are used to recognize activities. A radial basis function neural network (RBFNN) with localized stochastic-sensitive autoencoder (LiSSA) method is proposed for the purposes of home-based activity recognition. An autoencoder (AE) is introduced to extract useful features from the binary sensor data by converting binary inputs into continuous inputs to extract increased levels of hidden information. The generalization capability of the proposed method is enhanced by minimizing both the training error and the stochastic sensitivity measure in an attempt to improve the ability of the classifier to tolerate uncertainties in the sensor data. Four binary home-based activity recognition datasets including OrdonezA, OrdonezB, Ulster, and activities of daily living data from van Kasteren (vanKasterenADL) are used to evaluate the effectiveness of the proposed method. Compared with well-known benchmarking approaches including support vector machine (SVM), multilayer perceptron neural network (MLPNN), random forest and an RBFNN-based method, the proposed method yielded the best performance with 98.35%, 86.26%, 96.31%, 92.31% accuracy on four datasets, respectively. which can be used to underpin a multitude of services such as personal health management [2], elderly care services [3], smart home services [4,5], to name but a few. However, it is a complicated process with many unsolved challenges such as multiple occupancy, interleaved activities, incomplete sensor data and differences in inter-and intra-inhabitant behaviors. As a result, due to the diversity of its data sources (smart home, smart wearable devices, mobile phones sensors and cameras), various solutions have been proposed to solve this problem [6].Some research studies in the area of activity recognition have been based on image data collected by cameras [7][8][9][10]. Limited by computational complexity and privacy issues, this type of activity recognition is mainly used in the field of public safety and human-computer interaction. As an alternative to image-based data, some research has been based on data collected from wearable devices and smartphones [11][12][13]. In this paper, we focus on home-based activity recognition, which is mainly used in elderly care service or smart home service provision. Binary data were collected through binary sensors embedded ...

show abstract

“…In [41] another Q-neighborhood based sensitivity was introduced to assess sensitivity for individual instances of the imbalanced classification problem. Recently, a stochastic sensitivity [42] based on L-GEM was introduced to provide a straightforward measure on an MLP's output fluctuations.…”

Section: A the Stochastic Sensitivity Analysis Of Neural Networkmentioning

confidence: 99%

Bilateral Sensitivity Analysis for Understandable Neural Networks and its application to Reservoir Engineering

Wang¹,

Zhang²,

Zhang³

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper, a model-independent sensitivity analysis for (deep) neural network, Bilateral Sensitivity Analysis (BiSA), is proposed to measure the relationship between neurons and layers. Both the BiSA between pair of layers and the BiSA between any pair neurons in different layers are defined for (deep) neural networks. This sensitivity can measure the influence or contribution from any layer to another layer behind this layer in the (deep) neural networks. It provides a helpful tool to interpret the learned model. The BiSA can also measure the influence or contribution from any neuron to another neuron in a subsequent layer and is critical to analyze the relationship between neurons in different layers. Then the BiSA from any input to any output of a network is easily defined to assess the connections between the inputs and outputs. The proposed BiSA of (deep) neural networks is then applied to characterize the well connectivity in reservoir engineering. Given a network trained by Water Injection Rates (WIRs) and Liquid Production Rates (LPRs) data, the well connectivity can be efficiently described through BiSA. The empirical results verify the effectiveness of the proposed method. The comparisons with the exiting methods demonstrate the robustness and the superior performance of the proposed method.

show abstract

MLPNN Training via a Multiobjective Optimization of Training Error and Stochastic Sensitivity

Cited by 64 publications

References 37 publications

Effect of Additive Noise for Multi-Layered Perceptron with AutoEncoders

Effect of Additive Noise for Multi-Layered Perceptron with AutoEncoders

Radial Basis Function Neural Network with Localized Stochastic-Sensitive Autoencoder for Home-Based Activity Recognition

Bilateral Sensitivity Analysis for Understandable Neural Networks and its application to Reservoir Engineering

Contact Info

Product

Resources

About