scholarly journals Cardinality Estimation of an SQL Query Using Recursive Neural Networks

2020 ◽  
pp. 41-52
Author(s):  
Davit Karamyan
Keyword(s):  
Neural Networks ◽  
Expression Vectors ◽  
Convolutional Network ◽  
Continuous Vector ◽  
Large Margin ◽  
Natural Properties ◽  
Complex Interactions ◽  
Operator Type ◽  
Recursive Neural Networks ◽  
Sql Query

To learn complex interactions between predicates and accurately estimate the cardinality of an SQL query, we develop a novel framework based on recursive tree-structured neural networks, which take into account the natural properties of logical expressions: compositionality and n-ary associativity. The proposed architecture is an extension of MSCN (multi-set convolutional network) for queries containing both conjunction and disjunction operators. The goal is to represent an arbitrary logical expression in a continuous vector space by combining sub-expression vectors according to the operator type. We compared the proposed approach with the histogram-based approach on the real-world dataset and showed that our approach significantly outperforms histograms with a large margin.

scholarly journals Cyber—Physical Attack Detection in Water Distribution Systems with Temporal Graph Convolutional Neural Networks

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1247
Author(s):  
Lydia Tsiami ◽  
Christos Makropoulos
Keyword(s):  
Neural Networks ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Attack Detection ◽  
Convolutional Network ◽  
Irreversible Damage ◽  
Physical Attack ◽  
Temporal Graph ◽  
Graph Neural Networks

Prompt detection of cyber–physical attacks (CPAs) on a water distribution system (WDS) is critical to avoid irreversible damage to the network infrastructure and disruption of water services. However, the complex interdependencies of the water network’s components make CPA detection challenging. To better capture the spatiotemporal dimensions of these interdependencies, we represented the WDS as a mathematical graph and approached the problem by utilizing graph neural networks. We presented an online, one-stage, prediction-based algorithm that implements the temporal graph convolutional network and makes use of the Mahalanobis distance. The algorithm exhibited strong detection performance and was capable of localizing the targeted network components for several benchmark attacks. We suggested that an important property of the proposed algorithm was its explainability, which allowed the extraction of useful information about how the model works and as such it is a step towards the creation of trustworthy AI algorithms for water applications. Additional insights into metrics commonly used to rank algorithm performance were also presented and discussed.

scholarly journals Recursive Neural Networks Based on PSO for Image Parsing

2013 ◽  
Vol 2013 ◽  
pp. 1-7
Author(s):  
Guo-Rong Cai ◽  
Shui-Li Chen
Keyword(s):  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Objective Function ◽  
State Of The Art ◽  
Pso Algorithm ◽  
Training Algorithm ◽  
Image Parsing ◽  
Swarm Optimization ◽  
Recursive Neural Networks ◽  
Parsing Algorithm

This paper presents an image parsing algorithm which is based on Particle Swarm Optimization (PSO) and Recursive Neural Networks (RNNs). State-of-the-art method such as traditional RNN-based parsing strategy uses L-BFGS over the complete data for learning the parameters. However, this could cause problems due to the nondifferentiable objective function. In order to solve this problem, the PSO algorithm has been employed to tune the weights of RNN for minimizing the objective. Experimental results obtained on the Stanford background dataset show that our PSO-based training algorithm outperforms traditional RNN, Pixel CRF, region-based energy, simultaneous MRF, and superpixel MRF.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

Sign in / Sign up

Export Citation Format

Share Document