Parsimonious extreme learning machine using recursive orthogonal least squares.

A multiple-input and multiple-output (MIMO) model, namely Recursive Orthogonal Least Square (ROLS) based radial basis function (RBF) is developed to estimate product compositions in a batch distillation process from temperature measurements. The process data is generated by simulating the differential equations of the batch distillation process, changing the initial feed composition and boiluprate from batch to batch. Moreover, the reflux ratio is also randomly varied within each batch to represent the exact dynamics of the batch distillation. Temperature and distillate composition is correlated by the RBF trained by ROLS algorithm. A Single RBF network estimate the quality of products in real-time. The results show that ROLS based estimator give correct composition estimations for a batch distillation process. The robustness of the ROLS algorithm and low computational requirement makes the estimator attractive for on-line use.

A localised forgetting method for on-line adaptation of gaussion RBFN models

Mapping natural language (NL) statements into SQL queries allows users to interact with systems through everyday language. Semantic parsing has seen a growing interest over the past decades. In this paper, we extend single hidden layer feedforward network (SLFN) by adding the Kullback-Liebler (KL) divergence parameter to its objective function. We refer to this algorithm as Sparse SLFN (S-SLFN) which can learn whether an SQL query answers a particular NL question. With Bag of Words (BoW) representing the questions and the queries, the algorithm, by enforcing sparsity, is meant to retain robust features representing informative relationships and structure of the data. Experimental results show that S-SLFN outperforms SLFN and other algorithms for the GeoQueries dataset by a respectable margin.KeywordsSingle-hidden Layer Feedforward Network (SLFN)SparsitySemantic Parsing

Since real-world data sets usually contain large instances, it is meaningful to develop efficient and effective multiple instance learning (MIL) algorithm. As a learning paradigm, MIL is different from traditional supervised learning that handles the classification of bags comprising unlabeled instances. In this paper, a novel efficient method based on extreme learning machine (ELM) is proposed to address MIL problem. First, the most qualified instance is selected in each bag through a single hidden layer feedforward network (SLFN) whose input and output weights are both initialed randomly, and the single selected instance is used to represent every bag. Second, the modified ELM model is trained by using the selected instances to update the output weights. Experiments on several benchmark data sets and multiple instance regression data sets show that the ELM-MIL achieves good performance; moreover, it runs several times or even hundreds of times faster than other similar MIL algorithms.

Manifold learning in local tangent space via extreme learning machine

We attempt to quantify the significance of increasing the number of neurons in the hidden layer of a feedforward neural network architecture using the singular value decomposition (SVD). Through this, we extend some well-known properties of the SVD in evaluating the generalizability of single hidden layer feedforward networks (SLFNs) with respect to the number of hidden neurons. The generalization capability of the SLFN is measured by the degree of linear independency of the patterns in hidden layer space, which can be indirectly quantified from the singular values obtained from the SVD, in a post-learning step.

This paper addresses a terminal sliding mode strategy to control the attitude of quadrotor while achieving the finite time convergence. To deal with system uncertainty and time-varying disturbance, a hybrid controller using single-hidden layer feedforward network (SLFN) and disturbance observer (DOB) is proposed. Fast terminal sliding mode surface is designed to construct the sliding mode control. To improve learning speed, the updating law of SLFN weight utilizes the information of the fast terminal sliding mode. The effectiveness of the proposed controller is demonstrated with simulation example.

Two-stage extreme learning machine for regression

Image receptive fields for artificial neural networks

Extreme learning machine (ELM) was extended from the generalized single hidden layer feedforward networks where the input weights of the hidden layer nodes can be assigned randomly. It has been widely used for its much faster learning speed and less manual works. Considering the field of multi-label text classification, in this paper, we propose an ELM based algorithm combined with \(L_{21}\)-norm minimization of the output weights matrix called \(L_{21}\)-norm Minimization ELM, which not only fully inherits the merits of ELM but also facilitates group sparsity and reduces complexity of the learning model. Extensive experiments on several benchmark data sets show a more desirable performance compared with other common multi-label classification algorithms.

In this paper, we present a novel approach to model and classify gait patterns based on internal models. An internal model consists of two sets of differential equations and a neural network in between. It can effectively describe dynamic movement primitives (DMP), hence is able to model the temporal-spatial gait patterns. An interesting feature of the internal model is, the nonlinear map generated by the neural network can also serve the purpose for gait pattern classification. In this work we use a single hidden layer feedforward network (SLFN), and show that the characteristics of gait patterns can be captured via the output layer weights. The experiment results based on EMGs of gait patterns at five different walking speeds are used to validate the internal model approach.

With multiple antennas’ transmission, multiple-input multiple-output (MIMO) technique is able to utilize the space diversity to obtain high spectrum efficiency. In this study, we propose a single hidden layer feedforward network trained with extreme learning machine (ELM) to estimate channel performances in MIMO system. Bit error rate (BER) and signal-to-noise ratio (SNR) performance of back-propagation (BP) algorithm are also compared with our proposed neural network. The simulation results show that ELM has got much better time efficiency than BP in MIMO modeling. Furthermore, MIMO modeling based on ELM doesn’t need to send pilot, which reduce the waste of spectrum resources.

In this paper, we develop an online sequential learning algorithm for single hidden layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes in a unified framework. The algorithm is referred to as online sequential extreme learning machine (OS-ELM) and can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size. The activation functions for additive nodes in OS-ELM can be any bounded nonconstant piecewise continuous functions and the activation functions for RBF nodes can be any integrable piecewise continuous functions. In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. The algorithm uses the ideas of ELM of Huang et al. developed for batch learning which has been shown to be extremely fast with generalization performance better than other batch training methods. Apart from selecting the number of hidden nodes, no other control parameters have to be manually chosen. Detailed performance comparison of OS-ELM is done with other popular sequential learning algorithms on benchmark problems drawn from the regression, classification and time series prediction areas. The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance.

In this work, we address some issues in the classification of varying length patterns of speech represented as sets of continuous-valued feature vectors using kernel methods. Kernels designed for varying length patterns are called as dynamic kernels. We propose two dynamic kernels namely segment-level pyramid match kernel (SLPMK) and segment-level probabilistic sequence kernel (SLPSK) for classification of long duration speech, represented as varying length sets of feature vectors using extreme learning machine (ELM). SLPMK and SLPSK are designed by partitioning the speech signal into increasingly finer segments and matching the corresponding segments. SLPSK is built upon a set of Gaussian basis functions, where half of the basis functions contain class-specific information while the other half implicates the common characteristics of all the speech utterances of all classes. The computational complexity of SVM training algorithms is usually intensive, which is at least quadratic with respect to the number of training examples. It is difficult to deal with the immense amount of data using traditional SVMs. For reducing the training time of classifier we propose to use a simple algorithm namely ELM. ELM refers to a wider type of generalized single hidden layer feedforward networks (SLFNs) whose hidden layer need not be tuned. In our work, we proposed to explore kernel based ELM to exploit dynamic kernels. We study the performance of the ELM-based classifiers using the proposed SLPSK and SLPMK for speech emotion recognition and speaker identification tasks and compare with other kernels for varying length patterns. Experimental studies showed that proposed ELM-based approach offer a 10–12% of relative improvement over baseline approach, and a 3–9% relative improvement over ELMs/SVMs using other state-of-the-art dynamic kernels.

Credit risk evaluation has become an increasingly important field in financial risk management for financial institutions, especially for banks and credit card companies. Many data mining and statistical methods have been applied to this field. Extreme learning machine (ELM) classifier as a type of generalized single hidden layer feed-forward networks has been used in many applications and achieve good classification accuracy. Thus, we use ELM (kernel based) as a classification tool to perform the credit risk evaluation in this paper. The simulations are done on two credit risk evaluation datasets with three different kernel functions. Simulation results show that the kernel based ELM is more suitable for credit risk evaluation than the popular used Support Vector Machines (SVMs) with consideration of overall, good and bad accuracies.