On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks

Samiee, Kaveh; Iosifidis, Alexandros; Gabbouj, Moncef

doi:10.1016/j.eswa.2017.04.025

Cited by 5 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where η is the learning rate, x i is an m-dimensional input vector (input neuron), and y i � w T i x i y i � x T i w i (output Mathematical Problems in Engineering neuron) is the output. e new and old synapse weights are w i+1 and w i , respectively, and the weight change is given as Δw [41].…”

Section: Training Framework and Procedurementioning

confidence: 99%

A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

Matindife

Sun

Wang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In a smart home, the nonintrusive load monitoring recognition scheme normally achieves high appliance recognition performance in the case where the appliance signals have widely varying power levels and signature characteristics. However, it becomes more difficult to recognize appliances with equal or very close power specifications, often with almost identical signature characteristics. In literature, complex methods based on transient event detection and multiple classifiers that operate on different hand crafted features of the signal have been proposed to tackle this issue. In this paper, we propose a deep learning approach that dispenses with the complex transient event detection and hand crafting of signal features to provide high performance recognition of close tolerance appliances. The appliance classification is premised on the deep multilayer perceptron having three appliance signal parameters as input to increase the number of trainable samples and hence accuracy. In the case where we have limited data, we implement a transfer learning-based appliance classification strategy. With the view of obtaining an appropriate high performing disaggregation deep learning network for the said problem, we explore individually three deep learning disaggregation algorithms based on the multiple parallel structure convolutional neural networks, the recurrent neural network with parallel dense layers for a shared input, and the hybrid convolutional recurrent neural network. We disaggregate a total of three signal parameters per appliance in each case. To evaluate the performance of the proposed method, some simulations and comparisons have been carried out, and the results show that the proposed method can achieve promising performance.

show abstract

Section: Training Framework and Procedurementioning

confidence: 99%

A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

Matindife

Sun

Wang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Rosanna et al [15] used the metric between distributions, the l2 Wasserstein distance to proposed a PCA-based method for distributional-valued data. Yining and Joe [16] proposed a dynamic inner PCA framework for the modeling of dynamic data through the maximization of the covariance between a component and the prediction based on its previous values. In this method, a dynamic latent variable model is first extracted to portray the most auto-covarying dynamics in a given dataset.…”

Section: Literature Surveymentioning

confidence: 99%

“…It is primarily applied in PCA. From the computational perspective, the GHA [16,17] is beneficial because it can solve eigenvalue problems using iterative methods which requires no direct covariance matrix computation. This is more significant when there are many attributes in a given set [18,19].…”

Section: Generalized Hebbian Algorithm (Gha)mentioning

confidence: 99%

“…This is more significant when there are many attributes in a given set [18,19]. Oja and Karhunen [16] demonstrated an incremental solution to finding the first eigenvector from data arriving in the form of serial data items presented as vectors [7,20]. Later, Sanger [21] generalized this to the use of GHA to find the first N eigenvectors.…”

Section: Generalized Hebbian Algorithm (Gha)mentioning

confidence: 99%

See 1 more Smart Citation

Fuzzy Generalized Hebbian Algorithm for Large-Scale Intrusion Detection System

Ali¹,

Aljanabi

Ahmed

2020

IJIE

View full text Add to dashboard Cite

The huge number of irrelevant and redundant data used in building intrusion detection systems (IDS) is one of the common issues in network intrusion detection systems. This paper proposed the use of Fuzzy Generalized Hebbian Algorithm as a novel data reduction method to overcome this problem of data redundancy in IDS. Two methods for dimensionality reduction (GHA and Fuzzy GHA) were used and compared in this study. This allowed retaining the most relevant traffic data information from the network. Furthermore, the K Nearest Neighbor algorithm was applied for the classification of the test connections into 2 categories (attack or normal). The investigations were carried out on the KDDCUP '99 dataset and the results showed the Fuzzy GHA method to perform better than GHA in the detection of both U2R and DoS attacks.

show abstract

A novel robust ensemble model integrated extreme learning machine with multi-activation functions for energy modeling and analysis: Application to petrochemical industry

Zhang

Zhu

et al. 2018

Energy

View full text Add to dashboard Cite

On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks

Cited by 5 publications

References 31 publications

A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

Fuzzy Generalized Hebbian Algorithm for Large-Scale Intrusion Detection System

A novel robust ensemble model integrated extreme learning machine with multi-activation functions for energy modeling and analysis: Application to petrochemical industry

Contact Info

Product

Resources

About