Machine learning qualifies computers to assimilate with data, without being solely programmed [1, 2]. Machine learning can be classified as supervised and unsupervised learning. In supervised learning, computers learn...
详细信息
Fuzzy Cognitive Maps method combines the advantages of Fuzzy Logic, such as their human reasoning and linguistic features, with the advantages of Neural Networks, such as their low mathematical calculation requirement...
详细信息
Fuzzy Cognitive Maps method combines the advantages of Fuzzy Logic, such as their human reasoning and linguistic features, with the advantages of Neural Networks, such as their low mathematical calculation requirements, in order to model complex dynamic systems on a wide variety of applications. The system variables and their interconnections are described using a graph and a weight matrix. Application of experts’ knowledge leads towards more realistic system models. In addition, the implementation of state-space theory in combination with learning algorithms, lead to a new generation of Fuzzy Cognitive Maps, the Advanced State Fuzzy Cognitive Maps. All the above are implemented on a nearly Zero Energy Building model, using real weather data and presenting its annual energy response.
In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries. To this end, we formulate the task as a positive-unlabeled (PU) learning problem and ...
详细信息
ISBN:
(纸本)9781950737482
In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries. To this end, we formulate the task as a positive-unlabeled (PU) learning problem and accordingly propose a novel PU learning algorithm to perform the task. We prove that the proposed algorithm can unbiasedly and consistently estimate the task loss as if there is fully labeled data. A key feature of the proposed method is that it does not require the dictionaries to label every entity within a sentence, and it even does not require the dictionaries to label all of the words constituting an entity. This greatly reduces the requirement on the quality of the dictionaries and makes our method generalize well with quite simple dictionaries. Empirical studies on four public NER datasets demonstrate the effectiveness of our proposed method. We have published the source code at https : // ***/v-mipeng/LexiconNER.
The mine production scheduling problem (MPSP) has been studied since the 1960s, and remains an active area of computational research. In extending the concepts of the MPSP, the automated mine may now be regarded as a ...
详细信息
Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing framewo...
详细信息
ISBN:
(纸本)9781950737482
Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing framework with the dual learning algorithm, which enables a semantic parser to make full use of data (labeled and even unlabeled) through a dual-learning game. This game between a primal model (semantic parsing) and a dual model (logical form to query) forces them to regularize each other, and can achieve feedback signals from some prior-knowledge. By utilizing the prior-knowledge of logical form structures, we propose a novel reward signal at the surface and semantic levels which tends to generate complete and reasonable logical forms. Experimental results show that our approach achieves new state-of-the-art performance on ATIS dataset and gets competitive performance on OVERNIGHT dataset.
In this paper, differential and discrete linear systems with the affine model of parametric uncertainty are considered. A new method of iterative learning control design for such systems is proposed. This method is ba...
详细信息
In this paper, a novel cloud computing framework is presented with machine learning (ML) algorithms for aerospace applications such as condition based maintenance, detecting anomalies, predicting the onset of part fai...
详细信息
ISBN:
(纸本)1601322461
In this paper, a novel cloud computing framework is presented with machine learning (ML) algorithms for aerospace applications such as condition based maintenance, detecting anomalies, predicting the onset of part failures, and reducing total lifecycle costs. This cloud framework has been developed by using MapReduce, HBase, and Hadoop Distributed File System (HDFS) technologies on a Hadoop cluster of OpenSUSE Lima machines. Its ML algorithms are based on Mahout ML Library and its web portal is built using JBoss and JDK. Importantly, the big data from various Honeywell data sources are managed by our HBase and analyzed by various ML algorithms. Users can use this cloud based analytic toolset through web browsers anytime and anywhere. More analytic results of using this framework will be published later.
Stochastic vector quantization methods have been extensively studied in supervised and unsupervised learning problems as online, data-driven, interpretable, robust, and fast to train and evaluate algorithms. Being pro...
详细信息
Stochastic vector quantization methods have been extensively studied in supervised and unsupervised learning problems as online, data-driven, interpretable, robust, and fast to train and evaluate algorithms. Being prototype-based methods, they depend on a dissimilarity measure, which is both necessary and sufficient to belong to the family of Bregman divergences, if the mean value is used as the representative of the cluster. In this work, we investigate the convergence properties of stochastic vector quantization (VQ) and its supervised counterpart, learning Vector Quantization (LVQ), using Bregman divergences. We employ the theory of stochastic approximation to study the conditions on the initialization and the Bregman divergence generating functions, under which, the algorithms converge to desired configurations. These results formally support the use of Bregman divergences, such as the Kullback-Leibler divergence, in vector quantization algorithms.
For highly precise motion of a galvanometer scanner that tracks a periodic motion reference, learning control significantly decreases the tracking error. To achieve higher quality motion by reducing the angular sensor...
详细信息
For highly precise motion of a galvanometer scanner that tracks a periodic motion reference, learning control significantly decreases the tracking error. To achieve higher quality motion by reducing the angular sensor noise, this paper investigates inversion-based iterative control (IIC) that can learn only at the fundamental and harmonic frequencies of the periodic motion reference. This enables to separate the compensable tracking error from the noise to be eliminated during learning in the frequency domain. The analysis in the paper reveals a tradeoff for the noise reduction in the IIC design, and this paper proposes an equation to quickly tune a design parameter in the tradeoff for better performance. Furthermore, the effectiveness of the IIC algorithm is experimentally demonstrated for a galvanometer scanner. When the galvanometer scanner tracks a 20 Hz triangular motion of ± 10 degrees, the IIC successfully decreases the residual tracking error by 41 % to 2.83 ×10 -4 deg, by utilizing the noise reduction.
Based on hyperspectral technology, a BP neural network classification model based on sparrow algorithm was proposed to solve the shortage of fast classification technology of milk. The experimental samples were five k...
详细信息
暂无评论