Search

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

This paper describes a method of structural pattern recognition based on a genetic evolution processing of data structures with neural networks representation. Conventionally, one of the most popular learning formulations of data Structure processing is Backpropagation Through Structures (BPTS) [7]. The BPTS algorithm has been successfully applied to a number of learning tasks that involved structural patterns such as image, shape, and texture classifications. However, this BPTS typed algorithm suffers from the long-term dependency problem in learning very deep tree structures. In this paper, we propose the genetic evolution for this data structures processing. The idea of this algorithm is to tune the learning parameters by the genetic evolution with specified chromosome structures. Also, the fitness evaluation as well as the adaptive crossover and mutation for this structural genetic processing are investigated in this paper. An application to flowers image classification by a structural representation is provided for the validation of our method. The obtained results significantly support the capabilities of our proposed approach to classify and recognize flowers in terms of generalization and noise robustness. [ABSTRACT FROM AUTHOR]

In this paper, we propose a simple, flexible, and efficient hybrid spell checking methodology based upon phonetic matching, supervised learning, and associative matching in the AURA neural system. We integrate Hamming Distance and n-gram algorithms that have high recall for typing errors and a phonetic spell-checking algorithm in a single novel architecture. Our approach is suitable for any spell checking application though aimed toward isolated word error correction, particularly spell checking user queries in a search engine. We use a novel scoring scheme to integrate the retrieved words from each spelling approach and calculate an overall score for each matched word. From the overall scores, we can rank the possible matches. In this paper, we evaluate our approach against several benchmark spellchecking algorithms for recall accuracy. Our proposed hybrid methodology has the highest recall rate of the techniques evaluated. The method has a high recall rate and low-computational cost. [ABSTRACT FROM AUTHOR]

Approximate Nearest Neighbor (ANN) search has become a popular approach for performing fast and efficient retrieval on very large-scale datasets in recent years, as the size and dimension of data grow continuously. In this paper, we propose a novel vector quantization method for ANN search which enables faster and more accurate retrieval on publicly available datasets. We define vector quantization as a multiple affine subspace learning problem and explore the quantization centroids on multiple affine subspaces. We propose an iterative approach to minimize the quantization error in order to create a novel quantization scheme, which outperforms the state-of-the-art algorithms. The computational cost of our method is also comparable to that of the competing methods. [ABSTRACT FROM PUBLISHER]

Caching valid regions of spatial queries at mobile clients is effective in reducing the number of queries submitted by mobile clients and query load on the server. However, mobile clients suffer from longer waiting time for the server to compute valid regions. We propose in this paper a proxy-based approach to continuous nearest-neighbor (NN) and window queries. The proxy creates estimated valid regions (EVRs) for mobile clients by exploiting spatial and temporal locality of spatial queries. For NN queries, we devise two new algorithms to accelerate EVR growth, leading the proxy to build effective EVRs even when the cache size is small. On the other hand, we propose to represent the EVRs of window queries in the form of vectors, called estimated window vectors (EWVs), to achieve larger estimated valid regions. This novel representation and the associated creation algorithm result in more effective EVRs of window queries. In addition, due to the distinct characteristics, we use separate index structures, namely EVR-tree and grid index, for NN queries and window queries, respectively. To further increase efficiency, we develop algorithms to exploit the results of NN queries to aid grid index growth, benefiting EWV creation of window queries. Similarly, the grid index is utilized to support NN query answering and EVR updating. We conduct several experiments for performance evaluation. The experimental results show that the proposed approach significantly outperforms the existing proxy-based approaches. [ABSTRACT FROM AUTHOR]

In multilabel learning, each instance in the training set is associated with a set of labels and the task is to output a label set whose size is unknown a priori for each unseen instance. In this paper, this problem is addressed in the way that a neural network algorithm named BP-MLL, i.e., Backpropagation for Multilabel Learning, is proposed. It is derived from the popular Backpropagation algorithm through employing a novel error function capturing the characteristics of multilabel learning, i.e., the labels belonging to an instance should be ranked higher than those not belonging to that instance. Applications to two real-world multilabel learning problems, i.e., functional genomics and text categorization, show that the performance of BP-MLL is superior to that of some well-established multilabel learning algorithms. [ABSTRACT FROM AUTHOR]

Classification of large data sets is an important data mining problem that has wide applications. Jumping Emerging Patterns (JEPs) are those itemsets whose supports increase abruptly from zero in one data set to nonzero in another data set. In this paper, we propose a fast, accurate, and less complex classifier based on a subset of JEPs, called Strong Jumping Emerging Patterns (SJEPs). The support constraint of SJEP removes potentially less useful JEPs while retaining those with high discriminating power. Previous algorithms based on the manipulation of border [1] as well as consEPMiner [2] cannot directly mine SJEPs. Here, we present a new tree-based algorithm for their efficient discovery. Experimental results show that: 1) the training of our classifier is typically 10 times faster than earlier approaches, 2) our classifier uses much fewer patterns than the JEP-Classifier [3] to achieve a similar (and, often, improved) accuracy, and 3) in many cases, it is superior to other state-of-the-art classification systems such as Naive Bayes, CBA, C4.5, and bagged and boosted versions of C4.5. We argue that SJEPs are high-quality patterns which possess the most differentiating power. As a consequence, they represent sufficient information for the construction of accurate classifiers. In addition, we generalize these patterns by introducing Noise-tolerant Emerging Patterns (NEPs) and Generalized Noise-tolerant Emerging Patterns (GNEPs). Our tree-based algorithms can be adopted to easily discover these variations. We experimentally demonstrate that SJEPs, NEPs, and GNEPs are extremely useful for building effective classifiers that can deal well with noise. [ABSTRACT FROM AUTHOR]

A range nearest-neighbor (RNN) query retrieves the nearest neighbor (NN) for every point in a range. It is a natural generalization of point and continuous nearest-neighbor queries and has many applications. In this paper, we consider the ranges as (hyper)rectangles and propose efficient in-memory processing and secondary memory pruning techniques for RNN queries in both 2D and high-dimensional spaces. These techniques are generalized for kRNN queries, which return the k nearest neighbors for every point in the range. In addition, we devise an auxiliary solution-based index EXO-tree to speed up any type of NN query. EXO-tree is orthogonal to any existing NN processing algorithm and, thus, can be transparently integrated. An extensive empirical study was conducted to evaluate the CPU and I/O performance of these techniques, and the study showed that they are efficient and robust under various data sets, query ranges, numbers of nearest neighbors, dimensions, and cache sizes. [ABSTRACT FROM AUTHOR]

Based on an effective clustering algorithm—Affinity Propagation (AP)—we present in this paper a novel semisupervised text clustering algorithm, called Seeds Affinity Propagation (SAP). There are two main contributions in our approach: 1) a new similarity metric that captures the structural information of texts, and 2) a novel seed construction method to improve the semisupervised clustering process. To study the performance of the new algorithm, we applied it to the benchmark data set Reuters-21578 and compared it to two state-of-the-art clustering algorithms, namely, k-means algorithm and the original AP algorithm. Furthermore, we have analyzed the individual impact of the two proposed contributions. Results show that the proposed similarity metric is more effective in text clustering (F-measures ca. 21 percent higher than in the AP algorithm) and the proposed semisupervised strategy achieves both better clustering results and faster convergence (using only 76 percent iterations of the original AP). The complete SAP algorithm obtains higher F-measure (ca. 40 percent improvement over k-means and AP) and lower entropy (ca. 28 percent decrease over k-means and AP), improves significantly clustering execution time (20 times faster) in respect that k-means, and provides enhanced robustness compared with all other methods. [ABSTRACT FROM PUBLISHER]

In this paper, we present a new type of spatial queries called Nearest Surrounder (NS) queries. An NS query determines the nearest polygon-shaped spatial objects (referred to as nearest surrounder objects) and their orientations with respect to a query point from an object set. Besides, we derive two NS query variants, namely, multitier NS (m-NS) queries and angle-constrained NS (ANS) queries. An m-NS query searches multiple layers of NS objects for the same range of angles from a query point. An ANS query searches for NS objects within a specified range of angles. To evaluate NS queries and their variants, we explore angle-based and distance-based bound properties of polygons, and devise two efficient algorithms, namely, Sweep and Ripple, based on R-tree. The algorithms access objects in an order according to their orientations and distances with respect to a given query point, respectively. They are efficient as they can finish a search with one index lookup. Besides, they can progressively deliver a query result. Through empirical studies, we evaluate the proposed algorithms and report their performance for both synthetic and real object sets. [ABSTRACT FROM AUTHOR]