scholarly journals Parallel Extreme Learning Machines Based on Frequency Multiplexing

2021 ◽  
Vol 12 (1) ◽  
pp. 214
Author(s):  
Alessandro Lupo ◽  
Serge Massar

In a recent work, we reported on an Extreme Learning Machine (ELM) implemented in a photonic system based on frequency multiplexing, where each wavelength of the light encodes a different neuron state. In the present work, we experimentally demonstrate the parallelization potentialities of this approach. We show that multiple frequency combs centered on different frequencies can copropagate in the same system, resulting in either multiple independent ELMs executed in parallel on the same substrate or a single ELM with an increased number of neurons. We experimentally tested the performances of both these operation modes on several classification tasks, employing up to three different light sources, each of which generates an independent frequency comb. We also numerically evaluated the performances of the system in configurations containing up to 15 different light sources.

Nanophotonics ◽  
2016 ◽  
Vol 5 (2) ◽  
pp. 231-243 ◽  
Author(s):  
Tobias Hansson ◽  
Stefan Wabnitz

AbstractMicroresonator frequency combs hold promise for enabling a new class of light sources that are simultaneously both broadband and coherent, and that could allow for a profusion of potential applications. In this article, we review various theoretical models for describing the temporal dynamics and formation of optical frequency combs. These models form the basis for performing numerical simulations that can be used in order to better understand the comb generation process, for example helping to identify the universal combcharacteristics and their different associated physical phenomena. Moreover, models allow for the study, design and optimization of comb properties prior to the fabrication of actual devices. We consider and derive theoretical formalisms based on the Ikeda map, the modal expansion approach, and the Lugiato-Lefever equation. We further discuss the generation of frequency combs in silicon resonators featuring multiphoton absorption and free-carrier effects. Additionally, we review comb stability properties and consider the role of modulational instability as well as of parametric instabilities due to the boundary conditions of the cavity. These instability mechanisms are the basis for comprehending the process of frequency comb formation, for identifying the different dynamical regimes and the associated dependence on the comb parameters. Finally, we also discuss the phenomena of continuous wave bi- and multistability and its relation to the observation of mode-locked cavity solitons.


2014 ◽  
Vol 548-549 ◽  
pp. 1735-1738 ◽  
Author(s):  
Jian Tang ◽  
Dong Yan ◽  
Li Jie Zhao

Modeling concrete compressive strength is useful to ensure quality of civil engineering. This paper aims to compare several Extreme learning machines (ELMs) based modeling approaches for predicting the concrete compressive strength. Normal ELM algorithm, Partial least square-based extreme learning machines (PLS-ELMs) algorithm and Kernel ELM (KELM) algorithm are used and evaluated. Results indicate that the normal ELMs algorithm has the highest modeling speed, and the KELM has the best prediction accuracy. Every method is validated for modeling concrete compressive strength. The appropriate modeling approach should be selected according different purposes.


2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Xinran Zhou ◽  
Zijian Liu ◽  
Congxu Zhu

To apply the single hidden-layer feedforward neural networks (SLFN) to identify time-varying system, online regularized extreme learning machine (ELM) with forgetting mechanism (FORELM) and online kernelized ELM with forgetting mechanism (FOKELM) are presented in this paper. The FORELM updates the output weights of SLFN recursively by using Sherman-Morrison formula, and it combines advantages of online sequential ELM with forgetting mechanism (FOS-ELM) and regularized online sequential ELM (ReOS-ELM); that is, it can capture the latest properties of identified system by studying a certain number of the newest samples and also can avoid issue of ill-conditioned matrix inversion by regularization. The FOKELM tackles the problem of matrix expansion of kernel based incremental ELM (KB-IELM) by deleting the oldest sample according to the block matrix inverse formula when samples occur continually. The experimental results show that the proposed FORELM and FOKELM have better stability than FOS-ELM and have higher accuracy than ReOS-ELM in nonstationary environments; moreover, FORELM and FOKELM have time efficiencies superiority over dynamic regression extreme learning machine (DR-ELM) under certain conditions.


Author(s):  
Adnan Omer Abuassba ◽  
Dezheng O. Zhang ◽  
Xiong Luo

Ensembles are known to reduce the risk of selecting the wrong model by aggregating all candidate models. Ensembles are known to be more accurate than single models. Accuracy has been identified as an important factor in explaining the success of ensembles. Several techniques have been proposed to improve ensemble accuracy. But, until now, no perfect one has been proposed. The focus of this research is on how to create accurate ensemble learning machine (ELM) in the context of classification to deal with supervised data, noisy data, imbalanced data, and semi-supervised data. To deal with mentioned issues, the authors propose a heterogeneous ELM ensemble. The proposed heterogeneous ensemble of ELMs (AELME) for classification has different ELM algorithms, including regularized ELM (RELM) and kernel ELM (KELM). The authors propose new diverse AdaBoost ensemble-based ELM (AELME) for binary and multiclass data classification to deal with the imbalanced data issue.


2018 ◽  
Vol 28 (9) ◽  
pp. 2583-2594
Author(s):  
Marcos O Prates

Extreme learning machines have gained a lot of attention by the machine learning community because of its interesting properties and computational advantages. With the increase in collection of information nowadays, many sources of data have missing information making statistical analysis harder or unfeasible. In this paper, we present a new model, coined spatial extreme learning machine, that combine spatial modeling with extreme learning machines keeping the nice properties of both methodologies and making it very flexible and robust. As explained throughout the text, the spatial extreme learning machines have many advantages in comparison with the traditional extreme learning machines. By a simulation study and a real data analysis we present how the spatial extreme learning machine can be used to improve imputation of missing data and uncertainty prediction estimation.


2020 ◽  
Vol 309 ◽  
pp. 04018
Author(s):  
Guangjie Hao ◽  
Menghong Yu ◽  
Zhen Su

The dredging output of suction dredger mainly comes from the suction density of the rake head. Accurate prediction of suction density is of great significance to improve the dredging output of suction dredger. In order to overcome the shortcomings of low accuracy and poor real-time performance of the current inhalation density prediction methods, a bat algorithm is proposed to optimize the inhalation density prediction method of extreme learning machine. The bat algorithms for optimizing extreme learning machines prediction model is constructed based on the measured construction data of “Xinhaifeng” Yangtze Estuary, and compared with other prediction models. Finally, the bat algorithms for optimizing extreme learning machines model is used to build the output simulator of inhalation density. Compared with the actual construction, the selection of control parameters is analyzed when the output of inhalation density is the best. Experients show that bat algorithms for optimizing extreme learning machines prediction has high accuracy and good stability, and can provide scientific and effective reference for yield prediction and construction guidance.


Author(s):  
KLAUS NEUMANN ◽  
MATTHIAS ROLF ◽  
JOCHEN JAKOB STEIL

The application of machine learning methods in the engineering of intelligent technical systems often requires the integration of continuous constraints like positivity, monotonicity, or bounded curvature in the learned function to guarantee a reliable performance. We show that the extreme learning machine is particularly well suited for this task. Constraints involving arbitrary derivatives of the learned function are effectively implemented through quadratic optimization because the learned function is linear in its parameters, and derivatives can be derived analytically. We further provide a constructive approach to verify that discretely sampled constraints are generalized to continuous regions and show how local violations of the constraint can be rectified by iterative re-learning. We demonstrate the approach on a practical and challenging control problem from robotics, illustrating also how the proposed method enables learning from few data samples if additional prior knowledge about the problem is available.


2016 ◽  
Vol 1 (2) ◽  
pp. 97 ◽  
Author(s):  
Ersa Christian Prakoso ◽  
Untari Novia Wisesty ◽  
Jondri .

<span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>Electroencephalography </em><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">atau sinyal EEG adalah salah satu biosignal yang marak menjadi topik<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">penelitian saat ini. Sinyal EEG memiliki banyak manfaat seperti pendeteksian epilepsi, gangguan<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">tidur, atau input dalam aplikasi komputer. Salah satu input yang dapat dideteksi berdasarkan sinyal<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">EEG adalah keadaan mata. Namun untuk digunakan sebagai input dalam aplikasi diperlukan<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">klasifikasi dengan performansi yang memadai. Oleh karena itu penulis akan dilakukan penelitian<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">dimana salah satu metode pembelajaran Jaringan Syaraf Tiruan yaitu <span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>Extreme Learning Machine</em><br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">(ELM) akan diimplementasikan untuk mengklasifikasikan kondisi mata berdasarkan sinyal EEG.<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">Dataset yang digunakan untuk melatih dan menguji model adalah dataset <span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>eye-state </em><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">yang<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">didonasikan oleh Oliver Roesler digabung dengan dataset yang berasal dari website <span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>repository</em><br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>Universitas of California, IrvineI </em><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">(UCI) . Terdapat 7 <span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>corpus </em><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">yang terdiri dari perekaman EEG<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">yang dilakukan kepada 4 orang berbeda, lalu ditambahkan 1 <span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>corpus </em><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">yang merupakan<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">penggabungan seluruh <span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;"><em>corpus </em><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">lain. Dari hasil pengujian yang dilakukan disimpulkan bahwa ELM<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">dapat digunakan untuk klasifikasi keadaan mata dengan akurasi mencapai 97,95% dengan waktu<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">latih hanya 0,81 detik jika masing-masing data digunakan secara terpisah, sedangkan<br /><span style="font-size: 9pt; color: #252525; font-style: normal; font-variant: normal;">penggabungan keseluruhan dataset hanya mencapai akurasi 78,94% dengan waktu latih 5,71 detik.</span></span></span></span></span></span></span></span></span></span></span></span></span></span><br style="font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px;" /></span></span></span></span></span></span></span></span></span></span></span></span></span>


2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Nan Liu ◽  
Jiuwen Cao ◽  
Zhiping Lin ◽  
Pin Pin Pek ◽  
Zhi Xiong Koh ◽  
...  

Voting-based extreme learning machine (V-ELM) was proposed to improve learning efficiency where majority voting was employed. V-ELM assumes that all individual classifiers contribute equally to the decision ensemble. However, in many real-world scenarios, this assumption does not work well. In this paper, we aim to enhance V-ELM by introducing weights to distinguish the importance of each individual ELM classifier in decision making. Genetic algorithm is used for optimizing these weights. This evolutionary V-ELM is named as EV-ELM. Results on several benchmark databases show that EV-ELM achieves the highest classification accuracy compared with V-ELM and ELM.


Symmetry ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 801
Author(s):  
Xinran Zhou ◽  
Xiaoyan Kui

The online sequential extreme learning machine with persistent regularization and forgetting factor (OSELM-PRFF) can avoid potential singularities or ill-posed problems of online sequential regularized extreme learning machines with forgetting factors (FR-OSELM), and is particularly suitable for modelling in non-stationary environments. However, existing algorithms for OSELM-PRFF are time-consuming or unstable in certain paradigms or parameters setups. This paper presents a novel algorithm for OSELM-PRFF, named “Cholesky factorization based” OSELM-PRFF (CF-OSELM-PRFF), which recurrently constructs an equation for extreme learning machine and efficiently solves the equation via Cholesky factorization during every cycle. CF-OSELM-PRFF deals with timeliness of samples by forgetting factor, and the regularization term in its cost function works persistently. CF-OSELM-PRFF can learn data one-by-one or chunk-by-chunk with a fixed or varying chunk size. Detailed performance comparisons between CF-OSELM-PRFF and relevant approaches are carried out on several regression problems. The numerical simulation results show that CF-OSELM-PRFF demonstrates higher computational efficiency than its counterparts, and can yield stable predictions.


Sign in / Sign up

Export Citation Format

Share Document