Context-Sensitive Weights for a Neural Network

2007 ◽  
pp. 29-39 ◽  
Author(s):  
Robert P. Arritt ◽  
Roy M. Turner
Keyword(s):  
Neural Network ◽  
Context Sensitive

A Dynamic and Semantically-Aware Technique for Document Clustering in Biomedical Literature

2009 ◽  
Vol 5 (4) ◽  
pp. 44-57 ◽  
Author(s):  
Min Song ◽  
Xiaohua Hu ◽  
Illhoi Yoo ◽  
Eric Koppel
Keyword(s):  
Neural Network ◽  
Information Retrieval ◽  
Cell Structure ◽  
Document Clustering ◽  
Biomedical Literature ◽  
Self Organizing Map ◽  
Context Sensitive ◽  
Growing Cell ◽  
Document Models ◽  
Clustering Quality

As an unsupervised learning process, document clustering has been used to improve information retrieval performance by grouping similar documents and to help text mining approaches by providing a high-quality input for them. In this article, the authors propose a novel hybrid clustering technique that incorporates semantic smoothing of document models into a neural network framework. Recently, it has been reported that the semantic smoothing model enhances the retrieval quality in Information Retrieval (IR). Inspired by that, the authors developed and applied a context-sensitive semantic smoothing model to boost accuracy of clustering that is generated by a dynamic growing cell structure algorithm, a variation of the neural network technique. They evaluated the proposed technique on biomedical article sets from MEDLINE, the largest biomedical digital library in the world. Their experimental evaluations show that the proposed algorithm significantly improves the clustering quality over the traditional clustering techniques including k-means and self-organizing map (SOM).

A Dynamic and Semantically-Aware Technique for Document Clustering in Biomedical Literature

2011 ◽  
pp. 307-319
Author(s):  
Min Song ◽  
Xiaohua Hu ◽  
Illhoi Yoo ◽  
Eric Koppel
Keyword(s):  
Neural Network ◽  
Information Retrieval ◽  
Cell Structure ◽  
Document Clustering ◽  
Biomedical Literature ◽  
Self Organizing Map ◽  
Context Sensitive ◽  
Growing Cell ◽  
The Neural Network ◽  
Structure Algorithm

As an unsupervised learning process, document clustering has been used to improve information retrieval performance by grouping similar documents and to help text mining approaches by providing a high-quality input for them. In this paper, the authors propose a novel hybrid clustering technique that incorporates semantic smoothing of document models into a neural network framework. Recently, it has been reported that the semantic smoothing model enhances the retrieval quality in Information Retrieval (IR). Inspired by that, the authors developed and applied a context-sensitive semantic smoothing model to boost accuracy of clustering that is generated by a dynamic growing cell structure algorithm, a variation of the neural network technique. They evaluated the proposed technique on biomedical article sets from MEDLINE, the largest biomedical digital library in the world. Their experimental evaluations show that the proposed algorithm significantly improves the clustering quality over the traditional clustering techniques including k-means and self-organizing map (SOM).

scholarly journals A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

2015 ◽  
Author(s):  
Alessandro Sordoni ◽  
Michel Galley ◽  
Michael Auli ◽  
Chris Brockett ◽  
Yangfeng Ji ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Approach ◽  
Neural Network Approach ◽  
Context Sensitive

Grayscale Image Segmentation With Quantum-Inspired Multilayer Self-Organizing Neural Network Architecture Endorsed by Context Sensitive Thresholding

2021 ◽  
pp. 197-227
Author(s):  
Pankaj Pal ◽  
Siddhartha Bhattacharyya ◽  
Nishtha Agrawal
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Network Architecture ◽  
Activation Function ◽  
Grayscale Image ◽  
Threshold Values ◽  
Neural Network Architecture ◽  
Context Sensitive ◽  
Segmentation Process ◽  
Sigmoidal Activation Function

A method for grayscale image segmentation is presented using a quantum-inspired self-organizing neural network architecture by proper selection of the threshold values of the multilevel sigmoidal activation function (MUSIG). The context-sensitive threshold values in the different positions of the image are measured based on the homogeneity of the image content and used to extract the object by means of effective thresholding of the multilevel sigmoidal activation function guided by the quantum superposition principle. The neural network architecture uses fuzzy theoretic concepts to assist in the segmentation process. The authors propose a grayscale image segmentation method endorsed by context-sensitive thresholding technique. This quantum-inspired multilayer neural network is adapted with self-organization. The architecture ensures the segmentation process for the real-life images as well as synthetic images by selecting intensity parameter as the threshold value.

scholarly journals Online Speech Recognition Using Multichannel Parallel Acoustic Score Computation and Deep Neural Network (DNN)- Based Voice-Activity Detector

2020 ◽  
Vol 10 (12) ◽  
pp. 4091 ◽  
Author(s):  
Yoo Rhee Oh ◽  
Kiyoung Park ◽  
Jeon Gyu Park
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Deep Neural Network ◽  
Computation Method ◽  
Acoustic Model ◽  
Voice Activity Detector ◽  
Context Sensitive ◽  
Speech Features ◽  
Voice Activity ◽  
Main Thread

This paper aims to design an online, low-latency, and high-performance speech recognition system using a bidirectional long short-term memory (BLSTM) acoustic model. To achieve this, we adopt a server-client model and a context-sensitive-chunk-based approach. The speech recognition server manages a main thread and a decoder thread for each client and one worker thread. The main thread communicates with the connected client, extracts speech features, and buffers the features. The decoder thread performs speech recognition, including the proposed multichannel parallel acoustic score computation of a BLSTM acoustic model, the proposed deep neural network-based voice activity detector, and Viterbi decoding. The proposed acoustic score computation method estimates the acoustic scores of a context-sensitive-chunk BLSTM acoustic model for the batched speech features from concurrent clients, using the worker thread. The proposed deep neural network-based voice activity detector detects short pauses in the utterance to reduce response latency, while the user utters long sentences. From the experiments of Korean speech recognition, the number of concurrent clients is increased from 22 to 44 using the proposed acoustic score computation. When combined with the frame skipping method, the number is further increased up to 59 clients with a small accuracy degradation. Moreover, the average user-perceived latency is reduced from 11.71 s to 3.09–5.41 s by using the proposed deep neural network-based voice activity detector.

Sign in / Sign up

Export Citation Format

Share Document