The Experts below are selected from a list of 255 Experts worldwide ranked by ideXlab platform
Shimeng Yu - One of the best experts on this subject based on the ideXlab platform.
-
demonstration of convolution kernel operation on resistive cross point array
IEEE Electron Device Letters, 2016Co-Authors: Pai-yu Chen, Shimeng YuAbstract:Convolution is the key operation in the convolutional neural network, one of the most popular deep learning algorithms. The implementation of the convolution kernel on the resistive cross-point array is different than the implementation of the matrix-Vector multiplication in prior works. In this letter, we propose a dimensional reduction of 2-D kernel matrix into 1-D Column Vector, i.e., a Column of the array, and enable the parallel readout of multiple 2-D kernels simultaneously. As a proof-of-concept demonstration, we use the Prewitt kernels to detect both horizontal and vertical edges of the $20 \times 20$ pixels of black-and-white MNIST handwritten digits. The experiments were performed on the fabricated $12 \times 12$ resistive cross-point array based on the Pt/HfO x /TiN structure. The experimental results of the Prewitt kernel operation perfectly matches the simulation results, indicating the feasibility of the proposed implementation methodology of the convolution kernel on resistive cross-point array.
Dinh Phung - One of the best experts on this subject based on the ideXlab platform.
-
a capsule network based embedding model for knowledge graph completion and search personalization
arXiv: Computation and Language, 2018Co-Authors: Dai Quoc Nguyen, Thanh Vu, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh PhungAbstract:In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples (subject, relation, object). Our CapsE represents each triple as a 3-Column matrix where each Column Vector represents the embedding of an element in the triple. This 3-Column matrix is then fed to a convolution layer where multiple filters are operated to generate different feature maps. These feature maps are reconstructed into corresponding capsules which are then routed to another capsule to produce a continuous Vector. The length of this Vector is used to measure the plausibility score of the triple. Our proposed CapsE obtains better performance than previous state-of-the-art embedding models for knowledge graph completion on two benchmark datasets WN18RR and FB15k-237, and outperforms strong search personalization baselines on SEARCH17.
-
a novel embedding model for knowledge base completion based on convolutional neural network
North American Chapter of the Association for Computational Linguistics, 2018Co-Authors: Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh PhungAbstract:In this paper, we propose a novel embedding model, named ConvKB, for knowledge base completion. Our model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases. In ConvKB, each triple (head entity, relation, tail entity) is represented as a 3-Column matrix where each Column Vector represents a triple element. This 3-Column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps. These feature maps are then concatenated into a single feature Vector representing the input triple. The feature Vector is multiplied with a weight Vector via a dot product to return a score. This score is then used to predict whether the triple is valid or not. Experiments show that ConvKB achieves better link prediction performance than previous state-of-the-art embedding models on two benchmark datasets WN18RR and FB15k-237.
Leung Tsang - One of the best experts on this subject based on the ideXlab platform.
-
a smfsia method for the electromagnetic scattering perfectly conducting random rough surface
2009Co-Authors: Chi Hou Chan, Leung TsangAbstract:With the recent development of the sparse-matrix flat-surface iterative approach (SMFSIA), the Monte Carlo simulations of scattering from two-dimensional (3-D scattering problem) random rough surface problems have become much more efficient [l]. In SMFSIA, the iterative procedure involves multiplication of a very large square matrix with a Column Vector. In this paper, we show that this CPU time-consuming procedure can be replaced by the fast Fourier transform (FFT). A numerical example is given by investigating electromagnetic wave scattering using SMFSIA with the fast Fourier transform. This new method provides a faster solution time without sacrificing numerical accuracy. Electromagnetic scattering from a perfectly conducting surface is based on the magnetic field integral equation.
-
wave scattering with uv multilevel partitioning method 2 three dimensional problem of nonpenetrable surface scattering
Radio Science, 2004Co-Authors: Leung Tsang, Dong Chen, Vikram JandhyalaAbstract:[1] A UV multilevel partitioning method (UV-MLP) is developed to solve scalar wave three-dimensional (3-D) scattering problem. The method consists of setting up a table of transmitting and receiving block size and their separation using fast coarse-coarse sampling. For a specific scattering problem with given geometry, the scattering structure is partitioned into multilevel blocks. By looking up the rank in the static problem, the impedance matrix for a given transmitting and receiving block is expressed into a product of U and V matrix. In this paper the method is illustrated by applying to a 3-D scattering problem of random nonpenetrable rough surface. The cases of Dirichelt and Neumann boundary conditions are treated. Numerical simulation results are illustrated. For 65,536 boundary unknowns on a rough surface, and using a single processor of 2.66 GHz, it takes about 34 CPU min and 1.8 Gb of memory to compute the solution using conjugate gradient iterations and multilevel UV to accelerate the matrix-Column Vector multiplication.
-
a smfsia method for the electromagnetic scattering from a two dimensional 3 d scattering problem perfectly conducting random rough surface
IEEE Antennas and Propagation Society International Symposium, 1994Co-Authors: Chi Hou Chan, Leung TsangAbstract:With the development of the sparse-matrix flat-surface iterative approach (SMFSIA), the Monte Carlo simulations of scattering from two-dimensional (3-D scattering problem) random rough surface problems have become much more efficient. In SMFSIA, the iterative procedure involves multiplication of a very large square matrix with a Column Vector. The present authors show that this CPU time-consuming procedure can be replaced by the fast Fourier transform (FFT). A numerical example is given by investigating electromagnetic wave scattering using SMFSIA with the fast Fourier transform. This new method provides a faster solution time without sacrificing numerical accuracy. >
Phung Dinh - One of the best experts on this subject based on the ideXlab platform.
-
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
'Association for Computational Linguistics (ACL)', 2018Co-Authors: Nguyen, Dai Quoc, Nguyen, Tu Dinh, Nguyen, Dat Quoc, Phung DinhAbstract:In this paper, we propose a novel embedding model, named ConvKB, for knowledge base completion. Our model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases. In ConvKB, each triple (head entity, relation, tail entity) is represented as a 3-Column matrix where each Column Vector represents a triple element. This 3-Column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps. These feature maps are then concatenated into a single feature Vector representing the input triple. The feature Vector is multiplied with a weight Vector via a dot product to return a score. This score is then used to predict whether the triple is valid or not. Experiments show that ConvKB achieves better link prediction performance than previous state-of-the-art embedding models on two benchmark datasets WN18RR and FB15k-237.Comment: In Proceedings of NAACL-HLT 2018, to appea
Pai-yu Chen - One of the best experts on this subject based on the ideXlab platform.
-
demonstration of convolution kernel operation on resistive cross point array
IEEE Electron Device Letters, 2016Co-Authors: Pai-yu Chen, Shimeng YuAbstract:Convolution is the key operation in the convolutional neural network, one of the most popular deep learning algorithms. The implementation of the convolution kernel on the resistive cross-point array is different than the implementation of the matrix-Vector multiplication in prior works. In this letter, we propose a dimensional reduction of 2-D kernel matrix into 1-D Column Vector, i.e., a Column of the array, and enable the parallel readout of multiple 2-D kernels simultaneously. As a proof-of-concept demonstration, we use the Prewitt kernels to detect both horizontal and vertical edges of the $20 \times 20$ pixels of black-and-white MNIST handwritten digits. The experiments were performed on the fabricated $12 \times 12$ resistive cross-point array based on the Pt/HfO x /TiN structure. The experimental results of the Prewitt kernel operation perfectly matches the simulation results, indicating the feasibility of the proposed implementation methodology of the convolution kernel on resistive cross-point array.