« Home « Kết quả tìm kiếm

Convolutional neural networks

Tìm thấy 16+ kết quả cho từ khóa "Convolutional neural networks"

Human activity detection and action recognition in videos using convolutional neural networks

tailieu.vn

Proposed Method SIFT Feature Extraction, Optical Flow Computation, Convolutional Neural Networks Classifier. Proposed Method SIFT feature extraction, Optical flow computation, Convolutional Neural Networks Classifier. This paper focuses mainly on human action recognition and classification using machine learning techniques.

Cancer type prediction based on copy number aberration and chromatin 3D structure with convolutional neural networks

tailieu.vn

Cancer type prediction based on copy number aberration and chromatin 3D structure with convolutional neural networks. Experimental results on the COSMIC CNA dataset indicate that 2D CNN with both cell lines of HiC data lead to the best performance.

Plant identication using new architecture convolutional neural networks combine with replacing the red of color channel image by vein morphology leaf

tailieu.vn

Hinton, Imagenet classi¯cation with deep convolutional neural networks, Advances in Neural Information Processing Systems, Nevada, USA, 2012, pp. Parry, Leaf classi¯cation utilizing a convolutional neural network, SoutheastCon 2015 IEEE, Fort Lauderdale, FL, USA, 2015, pp. Soderkvist, Computer Vision Classi¯cation of Leaves from Swedish Trees (Linkoping University, Linkoping, 2001).. Xiang, A leaf recognition algorithm for plant classi¯cation using a probabilistic neural network, 2007 IEEE Int.

A hybrid model using the pre trained bert and deep neural networks with rich feature for extractive text summarization

tailieu.vn

Kim, Convolutional neural networks for sentence classification, in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Minh, Extractive multi-document summarization us- ing k-means, centroid-based method, mmr, and sentence position, in Proceedings of the Tenth International Symposium on Information and Communication Technology, 2019, pp.

Architectures and accuracy of artificial neural network for disease classification from omics data

tailieu.vn

Representative deep learning methods, Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN), were deployed and explored in seeking optimal architectures for the best classification performance. Furthermore, MLP was one of the most robust methods against imbalanced class composition and inaccurate class labels.. In the past decade, deep neural networks have inspired waves of novel applications for machine learning prob- lems.

An anatomy for neural search engines

tailieu.vn

Mesnil, Learning semantic representations using convolutional neural networks for web search, in: Proceedings of the Twenty-Third International Conference on World Wide Web, 2014, pp. Polosukhin , Attention is all you need, in: Proceedings of the Advances in Neural Information Processing Systems 30, Curran Associates, Inc., 2017, pp.

A combination of faster R-CNN and yolov2 for drone detection in images

tailieu.vn

This paper proposes a hybrid approach combining two emerging convolutional neural networks: Faster R-CNN and YOLOv2 to detect drones in images. Experimental results show that the approach can add up to almost 5% and more than 11% to precision and recall for Faster R-CNN and add up to 3% and more than 6% to these two metrics for YOLOv2. If a network is failed to detect drones in an image, the other network can help.. Convolutional Neural Network Faster R-CNN and YOLO Drone detection.

Improving hand posture recognition performance using multi-modalities

tailieu.vn

Kautz, Online detection and classification of dynamic hand gestures with recurrent 3d convolutional neural networks, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp.

Classifier-adaptation knowledge distillation framework for relation extraction and event detection with imbalanced data

tailieu.vn

Grishman, Relation extraction: Perspective from convolutional neural networks, in: Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing, 2015, pp. Sun, Graph neural networks with generated parameters for relation extraction, in: in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, pp.

Learning decomposed hierarchical feature for better transferability of deep models

tailieu.vn

Yang, Domain adaptation via transfer component analysis, IEEE Transactions on Neural Networks Ờ. Jordan, Deep transfer learning with joint adaptation networks, in: International Conference on Machine Learning (ICML), 2017.. Panchanathan, Deep hashing network for unsupervised domain adaptation, in: Proc. Feng, Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution, in: Proceedings of the IEEE International Conference on Computer Vision, 2019, pp.

Kết hợp đặc trưng diện mạo và chuyển động trong biểu diễn hoạt động của người sử dụng mạng nơ ron tích chập =

311861.pdf

dlib.hust.edu.vn

In chapter 3, we describe our proposed methods using3D convolutional neural network for action recognition with two-stream architecture. Inchapter 4, we report the result on UCF101, HMDB51, CMDFALL and analyse the result.Chapter 5 concludes and gives ideas for future works.14 Chapter 2State-of-the-art on HAR using CNN2.1 Introduction to Convolutional Neural NetworksConvolutional Neural Networks (CNN) are biologically-inspirire variants of MultilayerPerceptrons.

A multi-dimensional relation model for dimensional sentiment analysis

tailieu.vn

Shukla, Prayas at EmoInt 2017: An Ensemble of Deep Neural Architectures for Emotion Intensity Prediction in Tweets, in: Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA pp. Kim, Convolutional neural networks for sentence classification, in: Proceedings of the 14th Conference on Empirical Methods in Natural Language Processing (EMNLP pp.

Enhanced CNN models for binary and multiclass student classification on temporal educational data at the program level

tailieu.vn

In this context, we discuss the temporal aspects, sparseness, data overlapping, and data imbalance for both binary and multiclass classi¯cation at the program level.. 16, our work is also the ¯rst one that de¯nes a deep learning-based solution to the task which handles temporal data by means of image processing techniques, does image augmentation for more training data, and con- structs convolutional neural networks for both binary and multiclass classi¯cation..

MRCNN: A deep learning model for regression of genome-wide DNA methylation

tailieu.vn

In this paper, we propose a novel deep learning model based on convolutional neural networks for predicting DNA methylation at single-CpG-site precision using local DNA sequence. The extraction of DNA sequence features is achieved by multistep 2D-array-convolution, and the MSE loss function is min- imized to achieve regression of the methylation values..

RBPsuite: RNA-protein binding sites prediction suite based on deep learning

tailieu.vn

Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks. Pysster: classification of biological sequences by learning sequence and structure motifs with convolutional neural networks.. DeepCLIP: predicting the effect of mutations on protein-RNA binding with deep learning. Predicting RNA-protein binding sites and motifs through combining local and global deep convolutional neural networks..

Discerning novel splice junctions derived from RNA-seq alignment: A deep learning approach

tailieu.vn

Results: In this work, we present a deep learning based splice junction sequence classifier, named DeepSplice, which employs convolutional neural networks to classify candidate splice junctions.

A combination of neighborhood based ratio operator and convolutional wavelet neural networks for change detection in multi-temporal synthetic aperture radar images

tailieu.vn

Wang, "Sea ice change detection in SAR images based on convolutional-wavelet neural networks,". IEEE Geoscience and Remote Sensing Letters, vol.16, pp.. IEEE signal processing magazine, vol.22, pp

Nhận dạng tiếng nói điều khiển với convolutional neural network (CNN)

ctujsvn.ctu.edu.vn

NHẬN DẠNG TIẾNG NÓI ĐIỀU KHIỂN VỚI CONVOLUTIONAL NEURAL NETWORK (CNN). Từ khóa:. Convolutional neural network (CNN), deep neural network (DNN), keyword spooting (KWS) Keywords:. Convolutional neural network (CNN), deep neural network (DNN), keyword spooting (KWS). Bài báo trình bày một phương pháp nhận dạng tiếng nói điều khiển ngắn sử dụng đặc trưng MFCC (Mel frequency cepstral coefficients) và mô hình convolutional neural network (CNN).

Tổng quan về Neural Networks

tailieu.vn

Người sử dụng Neural Networks thu thập các dữ liệu đặc trưng, và sau đó gọi các thuật toán huấn luyện để có thể tự học cấu trúc của dữ liệu. Một tính năng khác của Neural Networks là nó có thể học mối liên hệ giữa ngõ vào và ngõ ra thông qua việc huấn luyện. Có hai loại huấn luyện sử dụng trong Neural Networks là huấn luyện có giám sát và không giám sát. Với những loại mạng khác nhau thì sử dụng các loại huấn luyện khác nhau. Huấn luyện có giám sát sử dụng thông dụng nhất..

Kalman Filtering and Neural Networks P2

tailieu.vn

Marko, ỔỔThe square root Kalman filter training of recurrent neural networks,ỖỖ in Proceedings of the 1998 IEEE Conference on Systems, Man and Cybernetics, Orlando, FL, pp. ỔỔThe application of dynamic neural networks to the estimation of feedgas vehicle emissions,ỖỖ in Proceedings of the 1998 International Joint Confer- ence on Neural Networks, Anchorage, AK, pp