scholarly journals Convolutional recurrent neural network with template based representation for complex question answering

2020 ◽  
Vol 10 (3) ◽  
pp. 2710
Author(s):  
A. Chandra Obula Reddy ◽  
K. Madhavi
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Question Answering ◽  
Internal Representation ◽  
Semantic Matching ◽  
Softmax Classifier ◽  
Questions And Answers ◽  
Fully Connected ◽  
The Given ◽  
Complex Question

Complex Question answering system is developed to answer different types of questions accurately. Initially the question from the natural language is transformed to an internal representation which captures the semantics and intent of the question. In the proposed work, internal representation is provided with templates instead of using synonyms or keywords. Then for each internal representation, it is mapped to relevant query against the knowledge base. In present work, the Template representation based Convolutional Recurrent Neural Network (T-CRNN) is proposed for selecting answer in Complex Question Answering (CQA) framework. Recurrent neural network is used to obtain the exact correlation between answers and questions and the semantic matching among the collection of answers. Initially, the process of learning is accomplished through Convolutional Neural Network (CNN) which represents the questions and answers separately. Then the representation with fixed length is produced for each question with the help of fully connected neural network. In order to design the semantic matching between the answers, the representation of Question Answer (QA) pair is given into the Recurrent Neural Network (RNN). Finally, for the given question, the correctly correlated answers are identified with the softmax classifier.

Bayesian Probability and Tanimoto Based Recurrent Neural Network for Question Answering System

2021 ◽  
Author(s):  
Veeraraghavan Jagannathan
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Question Answering ◽  
Bayesian Probability ◽  
Significant Information ◽  
Continuous Increase ◽  
Question Answering System ◽  
Relevant Result ◽  
Proper Nouns ◽  
Different Types

Question Answering (QA) has become one of the most significant information retrieval applications. Despite that, most of the question answering system focused to increase the user experience in finding the relevant result. Due to the continuous increase of web content, retrieving the relevant result faces a challenging issue in the Question Answering System (QAS). Thus, an effective Question Classification (QC), and retrieval approach named Bayesian probability and Tanimoto-based Recurrent Neural Network (RNN) are proposed in this research to differentiate the types of questions more efficiently. This research presented an analysis of different types of questions with respect to the grammatical structures. Various patterns are identified from the questions and the RNN classifier is used to classify the questions. The results obtained by the proposed Bayesian probability and Tanimoto-based RNN showed that the syntactic categories related to the domain-specific types of proper nouns, numeral numbers, and the common nouns enable the RNN classifier to reveal better result for different types of questions. However, the proposed approach obtained better performance in terms of precision, recall, and F-measure with the values of 90.14, 86.301, and 90.936 using dataset-2.

Combination of Recurrent Neural Network and Deep Learning for Robot Navigation Task in Off-Road Environment

Robotica ◽  
2019 ◽  
Vol 38 (8) ◽  
pp. 1450-1462
Author(s):  
Farinaz Alamiyan-Harandi ◽  
Vali Derhami ◽  
Fatemeh Jamshidi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Robot Navigation ◽  
Recurrent Network ◽  
Navigation Task ◽  
Sensory Data ◽  
Uneven Terrain ◽  
Target Network ◽  
Fully Connected

SUMMARYThis paper tackles the challenge of the necessity of using the sequence of past environment states as the controller’s inputs in a vision-based robot navigation task. In this task, a robot has to follow a given trajectory without falling in pits and missing its balance in uneven terrain, when the only sensory input is the raw image captured by a camera. The robot should distinguish big pits from small holes to decide between avoiding and passing over. In non-Markov processes such as the abovementioned task, the decision is done using past sensory data to ensure admissible performance. Applying images as sensory inputs naturally causes the curse of dimensionality difficulty. On the other hand, using sequences of past images intensifies this difficulty. In this paper, a new framework called recurrent deep learning (RDL) with combination of deep learning (DL) and recurrent neural network is proposed to cope with the above challenge. At first, the proper features are extracted from the raw image using DL. Then, these represented features plus some expert-defined features are used as the inputs of a fully connected recurrent network (as target network) to generate command control of the robot. To evaluate the proposed RDL framework, some experiments are established on WEBOTS and MATLAB co-simulation platform. The simulation results demonstrate the proposed framework outperforms the conventional controller based on DL for the navigation task in the uneven terrains.

scholarly journals Code Edit Recommendation Using a Recurrent Neural Network

2021 ◽  
Vol 11 (19) ◽  
pp. 9286
Author(s):  
Seonah Lee ◽  
Jaejun Lee ◽  
Sungwon Kang ◽  
Jongsun Ahn ◽  
Heetae Cho
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Association Rule ◽  
Association Rule Mining ◽  
Recommendation System ◽  
Software Evolution ◽  
Rule Mining ◽  
Mining Technique ◽  
Recommendation Accuracy ◽  
The Given

When performing software evolution tasks, developers spend a significant amount of time looking for files to modify. By recommending files to modify, a code edit recommendation system reduces the developer’s navigation time when conducting software evolution tasks. In this paper, we propose a code edit recommendation method using a recurrent neural network (CERNN). CERNN forms contexts that maintain the sequence of developers’ interactions to recommend files to edit and stops recommendations when the first recommendation becomes incorrect for the given evolution task. We evaluated our method by comparing it with the state-of-the-art method MI-EA that was developed based on the association rule mining technique. The result shows that our proposed method improves the average recommendation accuracy by approximately 5% over MI-EA (0.64 vs. 0.59 F-score).

scholarly journals Exudate Detection for Diabetic Retinopathy Using Pretrained Convolutional Neural Networks

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Muhammad Mateen ◽  
Junhao Wen ◽  
Nasrullah Nasrullah ◽  
Song Sun ◽  
Shaukat Hayat
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Transfer Learning ◽  
Region Of Interest ◽  
The Other ◽  
Previous Knowledge ◽  
Residual Network ◽  
Softmax Classifier ◽  
Fully Connected ◽  
Visual Geometry

In the field of ophthalmology, diabetic retinopathy (DR) is a major cause of blindness. DR is based on retinal lesions including exudate. Exudates have been found to be one of the signs and serious DR anomalies, so the proper detection of these lesions and the treatment should be done immediately to prevent loss of vision. In this paper, pretrained convolutional neural network- (CNN-) based framework has been proposed for the detection of exudate. Recently, deep CNNs were individually applied to solve the specific problems. But, pretrained CNN models with transfer learning can utilize the previous knowledge to solve the other related problems. In the proposed approach, initially data preprocessing is performed for standardization of exudate patches. Furthermore, region of interest (ROI) localization is used to localize the features of exudates, and then transfer learning is performed for feature extraction using pretrained CNN models (Inception-v3, Residual Network-50, and Visual Geometry Group Network-19). Moreover, the fused features from fully connected (FC) layers are fed into the softmax classifier for exudate classification. The performance of proposed framework has been analyzed using two well-known publicly available databases such as e-Ophtha and DIARETDB1. The experimental results demonstrate that the proposed pretrained CNN-based framework outperforms the existing techniques for the detection of exudates.

scholarly journals Automatic Estimation of the Dynamics of Channel Conductance Using a Recurrent Neural Network

2009 ◽  
Vol 2009 ◽  
pp. 1-10
Author(s):  
Masaaki Takahashi ◽  
Kiyohisa Natsume
Keyword(s):  
Neural Network ◽  
Differential Equations ◽  
Action Potential ◽  
Recurrent Neural Network ◽  
Time Course ◽  
Estimation Method ◽  
Giant Axon ◽  
Channel Conductance ◽  
Periodic Action ◽  
Fully Connected

In order to simulate neuronal electrical activities, we must estimate the dynamics of channel conductances from physiological experimental data. However, this approach requires the formulation of differential equations that express the time course of channel conductance. On the other hand, if the dynamics are automatically estimated, neuronal activities can be easily simulated. By using a recurrent neural network (RNN), it is possible to estimate the dynamics of channel conductances without formulating the differential equations. In the present study, we estimated the dynamics of the Na+ and K+ conductances of a squid giant axon using two different fully connected RNNs and were able to reproduce various neuronal activities of the axon. The reproduced activities were an action potential, a threshold, a refractory phenomenon, a rebound action potential, and periodic action potentials with a constant stimulation. RNNs can be trained using channels other than the Na+ and K+ channels. Therefore, using our RNN estimation method, the dynamics of channel conductance can be automatically estimated and the neuronal activities can be simulated using the channel RNNs. An RNN can be a useful tool to estimate the dynamics of the channel conductance of a neuron, and by using the method presented here, it is possible to simulate neuronal activities more easily than by using the previous methods.

scholarly journals Hierarchy based firefly optimized K-means clustering for complex question answering

2020 ◽  
Vol 17 (1) ◽  
pp. 264
Author(s):  
A. Chandra Obula Reddy ◽  
K. Madhavi
Keyword(s):  
Question Answering ◽  
Selection Process ◽  
Document Retrieval ◽  
Question Answering System ◽  
Candidate Solution ◽  
Firefly Optimization ◽  
The Given ◽  
Firefly Optimization Algorithm ◽  
Complex Question

Complex Question Answering (CQA) is commonly used for answering community questions which requires human knowledge for answering them. It is essential to find complex question answering system for avoiding the complexities behind the question answering system. In the present work, we proposed Hierarchy based Firefly Optimized k-means Clustering (HFO-KC) method for complex question answering. Initially, the given input query is preprocessed. It eliminates the way of misclassification when comparing the strings. In order to enhance the answer selection process, the obtained keywords are mapped into the candidate solution. After mapping, the obtained keywords are segmented. Each segmentation forms a new query for answer selection and various number of answers selected for each query. Okapi-25 similarity computation is utilized for the process of document retrieval. Then the answers selected are classified with K means clustering which forms the hierarchy for each answer. Finally the firefly optimization algorithm is used for selecting the best quality of answer from the hierarchy.

scholarly journals Nonlinear Autoregressive Recurrent Neural Network Model for Quality of Service Prediction

2020 ◽  
Vol 8 (6) ◽  
pp. 4762-4770
Keyword(s):  
Neural Network ◽  
Quality Of Service ◽  
Recurrent Neural Network ◽  
Prediction System ◽  
Qos Prediction ◽  
Proposed Model ◽  
Routing Monitoring ◽  
The Given ◽  
Nonlinear Autoregressive

Due to the advances in computer networks, Internet and multimedia communications, Quality of Service (QoS) monitoring and assessment become an increasingly important. The importance of assessing QoS stems from the fact it may reflect the resources availability of a network that may provide solutions for QoS provision, routing, monitoring, management … etc. In the literature, several monitoring and measurement approached and methods have been developed to quantify and predict the QoS of multimedia applications transmitted over such networks. In this research, a new QoS prediction system will be designed. The proposed system is based on using the Nonlinear Autoregressive with eXogenous input model (NARX) using recurrent neural network. This prediction system uses in addition to the QoS parameters; previous measured QoS values will used as inputs to this model. The expected output of this new model is the forecasted QoS. The proposed model will be trained, tested, validated and then optimized to provide a good estimate of the QoS provided by the given network. Simulation results are expected to show that the proposed model will have high accurate QoS prediction capabilities compared to other QoS assessment systems adopted in the literature.

scholarly journals FA3L at SemEval-2017 Task 3: A ThRee Embeddings Recurrent Neural Network for Question Answering

2017 ◽  
Author(s):  
Giuseppe Attardi ◽  
Antonio Carta ◽  
Federico Errica ◽  
Andrea Madotto ◽  
Ludovica Pannitto
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Question Answering

scholarly journals Discovery of Novel Chemical Reactions by Deep Generative Recurrent Neural Network

2020 ◽  
Author(s):  
William Bort ◽  
Igor I. Baskin ◽  
Pavel Sidorov ◽  
Gilles Marcou ◽  
Dragos Horvath ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Chemical Reactions ◽  
Recurrent Neural Network ◽  
Coupling Reactions ◽  
Two Dimensional ◽  
Topographic Map ◽  
Latent Space ◽  
The Given ◽  
Condensed Graph Of Reaction

Here, we report an application of Artificial Intelligence techniques to generate novel chemical reactions of the given type. A sequence-to-sequence autoencoder was trained on the USPTO reaction database. Each reaction was converted into a single Condensed Graph of Reaction (CGR), followed by their translation into on-purpose developed SMILES/GGR text strings. The autoencoder latent space was visualized on the two-dimensional generative topographic map, from which some zones populated by Suzuki coupling reactions were targeted. These served for the generation of novel reactions by sampling the latent space points and decoding them to SMILES/CGR.<br>

scholarly journals Recurrent Neural Network based Models for Word Prediction

2019 ◽  
Vol 8 (4) ◽  
pp. 7433-7437
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
English Language ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Memory Network ◽  
Long Short Term Memory ◽  
The Given ◽  
Current Word

Globally, people are spending a cumulative amount of time on their mobile device, laptop, tab, desktop, etc,. for messaging, sending emails, banking, interaction through social media, and all other activities. It is necessary to cut down the time spend on typing through these devices. It can be achieved when the device can provide the user more options for what the next word might be for the current typed word. It also increases the speed of typing. In this paper, we suggest and presented a comparative study on various models like Recurrent Neural Network, Stacked Recurrent Neural Network, Long Short Term Memory network (LSTM) and Bi-directional LSTM that gives solution for the above said problem. Our primary goal is to suggest the best model among the four models to predict the next word for the given current word in English Language. Our survey says that for predicting next word RNN provide accuracy 60% and loss 40%, Stacked RNN provide accuracy 62% and loss 38%, LSTM provide accuracy 64% and loss 36% and Bidirectional LSTM provide accuracy 72% and loss 28%.

Sign in / Sign up

Export Citation Format

Share Document