Search

The article discusses the deployment of machine learning technology in production environments. The authors describe the algorithms which constitute and shape machine learning protocols with a focus on papers on subjects including the MauveDB project to integrate machine learning technology into relational databases, scalable response prediction for online advertising, and optimization of neural network queries for object detection in video streams.

Spiking neural P (SN P) systems are a class of parallel computation models inspired by neurons, where the firing condition of a neuron is described by a regular expression associated with spiking rules. However, it is NP-complete to decide whether the number of spikes is in the length set of the language associated with the regular expression. In this paper, in order to avoid using regular expressions, two major and rather natural modifications in their form and functioning are proposed: the spiking rules no longer check the number of spikes in a neuron, but, in exchange, a polarization is associated with neurons and rules, one of the three electrical charges −, 0,+. Surprisingly enough, the computing devices obtained are still computationally complete, which are able to compute all Turing computable sets of natural numbers. On this basis, the number of neurons in a universal SN P system with polarizations is estimated. Several research directions are mentioned at the end of this paper. [ABSTRACT FROM AUTHOR]

In dynamic optimization problems (DOPs), as the environment changes through time, the optima also dynamically change. How to adapt to the dynamic environment and quickly find the optima in all environments is a challenging issue in solving DOPs. Usually, a new environment is strongly relevant to its previous environment. If we know how it changes from the previous environment to the new one, then we can transfer the information of the previous environment, e.g., past solutions, to get new promising information of the new environment, e.g., new high-quality solutions. Thus, in this paper, we propose a neural network (NN)-based information transfer method, named NNIT, to learn the transfer model of environment changes by NN and then use the learned model to reuse the past solutions. When the environment changes, NNIT first collects the solutions from both the previous environment and the new environment and then uses an NN to learn the transfer model from these solutions. After that, the NN is used to transfer the past solutions to new promising solutions for assisting the optimization in the new environment. The proposed NNIT can be incorporated into population-based evolutionary algorithms (EAs) to solve DOPs. Several typical state-of-the-art EAs for DOPs are selected for comprehensive study and evaluated using the widely used moving peaks benchmark. The experimental results show that the proposed NNIT is promising and can accelerate algorithm convergence. [ABSTRACT FROM AUTHOR]

Target-level sentiment analysis (TLSA) is a classification task to extract sentiments from targets in text. In this paper, we propose t arget-dependent c onvolutional n eural n etwork (TCNN) tailored to the task of TLSA. The TCNN leverages the distance information between the target word and its neighboring words to learn the importance of each word to the target. Experimental results show that the TCNN achieves state-of-the-art performance on both single- and multi-target datasets. Qualitative evaluations were conducted to demonstrate the limitations of previous TLSA methods and also to verify that distance information is crucial for TLSA. Furthermore, by exploiting a convolutional neural network (CNN), the TCNN trains six times faster per epoch than other baselines based on recurrent neural networks. [ABSTRACT FROM AUTHOR]

The paper addresses analytical and practical aspects of integration of equation-based (classical) and signal-derived [artificial neural network (ANN)] dynamic models for transient analysis of large-scale dynamical systems. Our signal-based part is based on two ANNs, and is derived from measurements at boundary points. In this paper, we describe this hybrid modeling technique, and focus on: 1) a least square-based mechanism for on-line correction of dynamic variable predictions that is based on actual operating conditions; 2) the resilience of the algorithm to missing measurements due to failed communication links; and 3) a complete two-way interaction between the differential-algebraic equation based subsystem and the ANN-based subsystem. The paper demonstrates the feasibility of implementing our approach in standard power system software by integrating the ANN-based model with the transient analysis toolbox from Matlab. We illustrate capabilities of the proposed approach for transient analysis on a benchmark multi-machine example derived from the New England/New-York interconnected power system. [ABSTRACT FROM AUTHOR]

Although hash function learning algorithms have achieved great success in recent years, most existing hash models are off-line, which are not suitable for processing sequential or online data. To address this problem, this paper proposes an online hash model to accommodate data coming in stream for online learning. Specifically, a new loss function is proposed to measure the similarity loss between a pair of data samples in hamming space. Then, a structured hash model is derived and optimized in a passive-aggressive way. Theoretical analysis on the upper bound of the cumulative loss for the proposed online hash model is provided. Furthermore, we extend our online hashing (OH) from a single model to a multimodel OH that trains multiple models so as to retain diverse OH models in order to avoid biased update. The competitive efficiency and effectiveness of the proposed online hash models are verified through extensive experiments on several large-scale data sets as compared with related hashing methods. [ABSTRACT FROM AUTHOR]

Abstract: All pairs shortest path (APSP) is a classical problem with diverse applications. Traditional algorithms are not suitable for real time applications, so it is necessary to investigate parallel algorithms. This paper presents an improved matrix multiplication method to solve the APSO problem. Afterwards, the pulse coupled neural network (PCNN) is employed to realize the parallel computation. The time complexity of our strategy is only , where n stands for the number of nodes. It is the fastest parallel algorithm compared to traditional PCNN, MOPCNN, and MPCNN methods. [Copyright &y& Elsevier]

Abstract: This paper proposes a hybrid modeling approach based on two familiar non-linear methods of mathematical modeling; the group method of data handling (GMDH) and differential evolution (DE) population-based algorithm. The proposed method constructs a GMDH self-organizing network model of a population of promising DE solutions. The new hybrid implementation is then applied to modeling tool wear in milling operations and also applied to two representative time series prediction problems of exchange rates of three international currencies and the well-studied Box-Jenkins gas furnace process data. The results of the proposed DE–GMDH approach are compared with the results obtained by the standard GMDH algorithm and its variants. Results presented show that the proposed DE–GMDH algorithm appears to perform better than the standard GMDH algorithm and the polynomial neural network (PNN) model for the tool wear problem. For the exchange rate problem, the results of the proposed DE–GMDH algorithm are competitive with all other approaches except in one case. For the Box-Jenkins gas furnace data, the experimental results clearly demonstrates that the proposed DE–GMDH-type network outperforms the existing models both in terms of better approximation capabilities as well as generalization abilities. Consequently, this self-organizing modeling approach may be useful in modeling advanced manufacturing systems where it is necessary to model tool wear during machining operations, and in time series applications such as in prediction of time series exchange rate and industrial gas furnace problems. [Copyright &y& Elsevier]

In this paper a modified algorithm is suggested for developing polynomial neural network (PN N) models. Optimal partial description (PD) modeling is introduced at each layer of the PNN expansion, a task accomplished using the orthogonal least squares (OLS) method. Based on the initial PD models determined by the polynomial order and the number of PD inputs, OLS selects the most significant regressor terms reducing the output error variance. The method produces PN N models exhibiting a high level of accuracy and superior generalization capabilities. Additionally, parsimonious models are obtained comprising a considerably smaller number of parameters compared to the ones generated by means of the conventional PNN algorithm. Three benchmark examples are elaborated, including modeling of the gas furnace process as well as the iris and wine classification problems. Extensive simulation results and comparison with other methods in the literature, demonstrate the effectiveness of the suggested modeling approach. [ABSTRACT FROM AUTHOR]

In this paper, we present a tabu search technique to approximately solve fuzzy optimization problems. We demonstrate the performance of the proposed method by applying it to an elementary fuzzy optimization problem. Other applications of the method to fuzzy linear programming, fuzzy regression and the training of fuzzy neural networks are also presented. [Copyright &y& Elsevier]