Distributed music classification using Random Vector Functional-Link nets

Scardapane, Simone; Fierimonte, Roberto; Wang, Dianhui; Panella, Massimo; Uncini, Aurelio

doi:10.1109/ijcnn.2015.7280333

Cited by 32 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We could make use of detrending techniques, such as mean-reverting approaches, in order to remove seasonal differences and spike outliers, as well as to improve the training accuracy. Additionally, it could be useful to test distributed learning approaches [51], by which the results could be improved sharing the data from different cabins of the same plant or from different nearby plants.…”

Section: Discussionmentioning

confidence: 99%

Prediction in Photovoltaic Power by Neural Networks

et al. 2017

Self Cite

View full text Add to dashboard Cite

Abstract:The ability to forecast the power produced by renewable energy plants in the short and middle term is a key issue to allow a high-level penetration of the distributed generation into the grid infrastructure. Forecasting energy production is mandatory for dispatching and distribution issues, at the transmission system operator level, as well as the electrical distributor and power system operator levels. In this paper, we present three techniques based on neural and fuzzy neural networks, namely the radial basis function, the adaptive neuro-fuzzy inference system and the higher-order neuro-fuzzy inference system, which are well suited to predict data sequences stemming from real-world applications. The preliminary results concerning the prediction of the power generated by a large-scale photovoltaic plant in Italy confirm the reliability and accuracy of the proposed approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction in Photovoltaic Power by Neural Networks

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, the consistent problem should be considered simultaneously in decentralized algorithms. The authors of References [22,39] believe the decentralized average consensus (DAC) method should be an acceptable choice for the consistent problem in decentralized training, and propose an algorithm based on the use of DAC, an extremely efficient procedure for computing global averages on a network which starts from local measurement vectors.…”

Section: Decentralized Training Algorithmmentioning

confidence: 99%

“…Previous literature indicates that Matlab is the preferred framework to test and verify new proposed algorithms [22,23,34,35,39]. On the other hand, in the Big Data era, several new processing frameworks have been proposed.…”

Section: Distributed Frameworkmentioning

confidence: 99%

“…However, in the era of Big Data, centralized data storage becomes technologically unsuitable [20]; as a result, solutions relying on centralized training in ML could face challenges such as single point of failure, communication bottlenecks, training consistency, etc. Meanwhile, in multiple real-world applications, large-scale training data is not possible to store in a centralized location, but large amounts of it are dispersed throughout a cluster of interconnected nodes (e.g., wireless sensor networks, peer-to-peer networks) [21][22][23]. Thus, a decentralized training algorithm for RNN/ESN, at any rate, would be an invaluable tool.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO

Wu¹,

Zhu²,

Li³

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

Abstract:The echo state network (ESN) employs a huge reservoir with sparsely and randomly connected internal nodes and only trains the output weights, which avoids the suboptimal problem, exploding and vanishing gradients, high complexity and other disadvantages faced by traditional recurrent neural network (RNN) training. In light of the outstanding adaption to nonlinear dynamical systems, ESN has been applied into a wide range of applications. However, in the era of Big Data, with an enormous amount of data being generated continuously every day, the data are often distributed and stored in real applications, and thus the centralized ESN training process is prone to being technologically unsuitable. In order to achieve the requirement of Big Data applications in the real world, in this study we propose an algorithm and its implementation for distributed ESN training. The mentioned algorithm is based on the parallel particle swarm optimization (P-PSO) technique and the implementation uses Spark, a famous large-scale data processing framework. Four extremely large-scale datasets, including artificial benchmarks, real-world data and image data, are adopted to verify our framework on a stretchable platform. Experimental results indicate that the proposed work is accurate in the era of Big Data, regarding speed, accuracy and generalization capabilities.

show abstract

“…Thanks to the presence of recurrent connections, RNNs are able to efficiently capture the dynamics in the underlying process to be learned. Tasks that would benefit from such algorithms abound, including distributed multimedia classification [12], event detection with array of microphones [13], classification of texts in cluster environments [14] and prediction of highly nonlinear time-series in wireless sensor networks [4]. Still, it is known that training an RNN model is a challenging task even in a centralized context, which is far from being fully solved [15]- [18].…”

Section: Introductionmentioning

confidence: 99%

Distributed Reservoir Computing with Sparse Readouts [Research Frontier]

Scardapane

Panella

Comminiello

et al. 2016

IEEE Comput. Intell. Mag.

Self Cite

View full text Add to dashboard Cite

In a network of agents, a widespread problem is the need to estimate a common underlying function starting from locally distributed measurements. Real-world scenarios may not allow the presence of centralized fusion centers, requiring the development of distributed, message-passing implementations of the standard machine learning training algorithms. In this paper, we are concerned with the distributed training of a particular class of recurrent neural networks, namely echo state networks (ESNs). In the centralized case, ESNs have received considerable attention, due to the fact that they can be trained with standard linear regression routines. Based on this observation, in our previous work we have introduced a decentralized algorithm, framed in the distributed optimization field, in order to train an ESN. In this paper, we focus on an additional sparsity property of the output layer of ESNs, allowing for very efficient implementations of the resulting networks. In order to evaluate the proposed algorithm, we test it on two well-known prediction benchmarks, namely the Mackey-Glass chaotic time series and the 10th order nonlinear auto regressive moving average (NARMA) system.

show abstract

Distributed music classification using Random Vector Functional-Link nets

Cited by 32 publications

References 27 publications

Prediction in Photovoltaic Power by Neural Networks

Prediction in Photovoltaic Power by Neural Networks

Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO

Distributed Reservoir Computing with Sparse Readouts [Research Frontier]

Contact Info

Product

Resources

About