Deep learning is a multilayer neural network learning algorithm which emerged in recent years. It has brought a new wave to machine learning, and making artificial intelligence and human-computer interaction advance w...
详细信息
Deep learning is a multilayer neural network learning algorithm which emerged in recent years. It has brought a new wave to machine learning, and making artificial intelligence and human-computer interaction advance with big strides. We applied deep learning to handwritten character recognition, and explored the two mainstream algorithm of deep learning: the Convolutional Neural Network (CNN) and the Deep Belief NetWork (DBN). We conduct the performance evaluation for CNN and DBN on the MNIST database and the real-world handwritten character database. The classification accuracy rate of CNN and DBN on the MNIST database is 99.28% and 98.12% respectively, and on the real-world handwritten character database is 92.91% and 91.66% respectively. The experiment results show that deep learning does have an excellent feature learning ability. It don't need to extract features manually. Deep learning can learn more nature features of the data.
Watershed algorithm was widely applied to have a better recognition and segmentation for the grains in metallographic image,due to its fuzziness,discontinuity and incompleteness around the boundary of metallographic *...
详细信息
Watershed algorithm was widely applied to have a better recognition and segmentation for the grains in metallographic image,due to its fuzziness,discontinuity and incompleteness around the boundary of metallographic *** this paper,in order to solve the defect of traditional watershed algorithm,metallographic image segmentation based on ridge detection and region-merger was *** the method of ridge region growing reconstructed the discontinuous ridge,making the most pseudo-blobs being marked in this ***,a method of similar adjacent region merging was proposed which could merge the pseudo-blobs,increasing merging *** experiments demonstrate that the proposed algorithm was able to solve over-segmentation and under-segmentation to the greatest extent,which could greatly increase the accuracy of segmentation of metallographic image.
This paper presents a new multi-class gene selection and classification method based on multiple support vector machine recursive feature elimination (SVM-RFE). For a multi-class DNA microarray problem, we solve it as...
详细信息
ISBN:
(纸本)9781479919611
This paper presents a new multi-class gene selection and classification method based on multiple support vector machine recursive feature elimination (SVM-RFE). For a multi-class DNA microarray problem, we solve it as multiple binary classification problems. First, the one-versus-all method is used to decompose the multi-class task into multiple binary problems. Second, an SVM-RFE is adopted to select genes for each binary problem. Then, an SVM classifier is used to train the selected gene data for a binary problem. Finally, we combine the outputs of multiple SVM classifiers. Experimental results on three DNA Microarray datasets show that the proposed method achieves higher classification accuracy.
Group Search Optimizer(GSO) is a swarm intelligence algorithm inspired from animal's foraging *** algorithm demonstrated its obvious superiority in solving complex engineering *** on the strategy of divide-and-con...
详细信息
ISBN:
(纸本)9781479970186
Group Search Optimizer(GSO) is a swarm intelligence algorithm inspired from animal's foraging *** algorithm demonstrated its obvious superiority in solving complex engineering *** on the strategy of divide-and-conquer and cooperative coevolution framework,a Cooperative Coevolutionary Multi-objective Group Search Optimizer(CMOGSO) is proposed in this *** CMOGSO,multi-objective optimization problems are decomposed according to their decision variables and are optimized by corresponding sub-groups *** are selected randomly from archive and employed to construct context vectors in order to evaluate the members in *** results demonstrate that CMOGSO can more effectively and efficiently solve multi-objective optimization problems compared with other evolutionary multi-objective optimizers.
Reordering models are one of essential components of statistical machine translation. In this paper, we propose a topic-based reordering model to predict orders for neighboring blocks by capturing topic-sensitive reor...
详细信息
Convolutional Neural Network (CNN) is a typical algorithm structure of deep learning and it has applied in image recognition field widely. Based on CNN, this paper puts forward a novel hybrid deep learning model CNN-E...
详细信息
This paper first presents a greedy algorithm for the K-median problem and then proves that the approximation ratio of the greedy algorithm is at most O(lnn). The test data shows that the greedy algorithm can get good ...
详细信息
The classification speed of SVM is inversely proportional to the number of Support Vectors (SVs). Therefore, the less SVs mean the more sparseness and the higher classification speed. In order to reduce the number of ...
详细信息
This paper proposes a method of semantic-based image retrieval using decision tree learning. The method includes two key points. (1) It can retrieve images with high-level semantics. Firstly we extract low-level featu...
详细信息
Considering the relative positions of the camera and object in three-dimensional space, there is always a perspective deformation, which affects the subsequent image processing, between the object in the image collect...
详细信息
暂无评论