Journal: Neural Computing and Applications

Abbreviation

Neural Comput & Applic

Publisher

Springer

Journal Volumes

ISSN

1433-3058
0941-0643

Description

Filters

2017 - 201912020 - 20244
Reset filters

Search Results

Publications1 - 5 of 5
  • Autoscaling Bloom filter: controlling trade-off between true and false positives
    Item type: Journal Article
    Kleyko, Denis; Rahimi, Abbas; Gayler, Ross W.; et al. (2020)
    Neural Computing and Applications
    A Bloom filter is a special case of an artificial neural network with two layers. Traditionally, it is seen as a simple data structure supporting membership queries on a set. The standard Bloom filter does not support the delete operation, and therefore, many applications use a counting Bloom filter to enable deletion. This paper proposes a generalization of the counting Bloom filter approach, called “autoscaling Bloom filters”, which allows adjustment of its capacity with probabilistic bounds on false positives and true positives. Thus, by relaxing the requirement on perfect true positive rate, the proposed autoscaling Bloom filter addresses the major difficulty of Bloom filters with respect to their scalability. In essence, the autoscaling Bloom filter is a binarized counting Bloom filter with an adjustable binarization threshold. We present the mathematical analysis of its performance and provide a procedure for minimizing its false positive rate.
  • Efficient but lightweight network for vehicle re-identification with center-constraint loss
    Item type: Journal Article
    Yu, Zhi; Zhu, Mingpeng (2022)
    Neural Computing and Applications
    Vehicle re-identification aims to retrieve the target vehicle from the image gallery quickly and accurately. Vehicle re-identification with deep learning has achieved considerable performance. However, most popular methods need construct complex network, which increases the calculation of network and difficulty of training. To balance performance and complexity, an efficient but lightweight network is proposed in this work. The designed network utilizes the global branch and the mask branch to extract the feature. The former can extract global feature efficiently. The latter can remove the changeable background based on the proposed mask-mapping module, which can map mask to feature map and adjust feature map dynamically. And then, the features from the original image and the mask-mapping module are fused to generate the final feature for vehicle re-identification. Besides, a novel center-constraint triplet loss is designed to optimize the proposed network and excavate more discriminate feature. Different from triplet loss, the proposed loss can consider more extra samples and constrain the center from positive sample set as well as negative sample set. To enhance the difference between hard samples and simple samples, an unequal weight strategy is embedded in this loss. The proposed method achieves 78.7% mAP with 95.4% Rank-1 on VeRi-776, and 84.3%, 80.7%, and 80.1% Rank-1 on three subsets from VehicleID, which demonstrates the effectiveness of the proposed method.
  • Training echo state networks for rotation-invariant bone marrow cell classification
    Item type: Journal Article
    Kainz, Philipp; Burgsteiner, Harald; Asslaber, Martin; et al. (2017)
    Neural Computing and Applications
    The main principle of diagnostic pathology is the reliable interpretation of individual cells in context of the tissue architecture. Especially a confident examination of bone marrow specimen is dependent on a valid classification of myeloid cells. In this work, we propose a novel rotation-invariant learning scheme for multi-class echo state networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity. The performance of our approach is compared to a classification random forest that learns rotation-invariance in a conventional way by exhaustively training on multiple rotations of individual samples. The methods were evaluated on a human bone marrow image database consisting of granulopoietic and erythropoietic cells in different maturation stages. Our ESN approach to cell classification does not rely on segmentation of cells or manual feature extraction and can therefore directly be applied to image data.
  • AnIO: anchored input–output learning for time-series forecasting
    Item type: Journal Article
    Stentoumi, Ourania; Nousi, Paraskevi; Tzelepi, Maria; et al. (2024)
    Neural Computing and Applications
    In this work, the short-term electric load demand forecasting problem is addressed, proposing a method inspired by the use of anchors in object detection methods. Specifically, a method named Anchored Input–Output Learning (AnIO) is proposed. AnIO proposes to define and use an anchor, reformulating the problem into offset prediction instead of actual load value prediction. Additionally, the use of anchor-encoded input features to match the encoded output is proposed. Extensive experiments were conducted, considering different anchors and model architectures on different datasets. Considering the Greek energy market, AnIO improves the performance from 2.914 to 2.251% in terms of MAPE. In conclusion, AnIO method achieves to improve the performance, considering time-series forecasting tasks.
  • Probabilistic neural network-based 2D travel-time tomography
    Item type: Journal Article
    Earp, Stephanie; Curtis, Andrew (2020)
    Neural Computing and Applications
    Travel-time tomography for the velocity structure of a medium is a highly nonlinear and nonunique inverse problem. Monte Carlo methods are becoming increasingly common choices to provide probabilistic solutions to tomographic problems but those methods are computationally expensive. Neural networks can often be used to solve highly nonlinear problems at a much lower computational cost when multiple inversions are needed from similar data types. We present the first method to perform fully nonlinear, rapid and probabilistic Bayesian inversion of travel-time data for 2D velocity maps using a mixture density network. We compare multiple methods to estimate probability density functions that represent the tomographic solution, using different sets of prior information and different training methodologies. We demonstrate the importance of prior information in such high-dimensional inverse problems due to the curse of dimensionality: unrealistically informative prior probability distributions may result in better estimates of the mean velocity structure; however, the uncertainties represented in the posterior probability density functions then contain less information than is obtained when using a less informative prior. This is illustrated by the emergence of uncertainty loops in posterior standard deviation maps when inverting travel-time data using a less informative prior, which are not observed when using networks trained on prior information that includes (unrealistic) a priori smoothness constraints in the velocity models. We show that after an expensive program of network training, repeated high-dimensional, probabilistic tomography is possible on timescales of the order of a second on a standard desktop computer.
Publications1 - 5 of 5