Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 12 of 12 for “"Bi-directional LSTM"”.

  1. Pre-trained CNN and bi-directional LSTM for no-reference video quality assessment

    … this challenge, we propose to use a stack of six bi-directional Long-Short Term Memory (LSTM) layers of different units to model temporal characteristics of video sequences. We feed this bi-directional LSTM network with spatial features extracted from video frames using pre-trained convolution …

    concordia Download PDF for Pre-trained CNN and bi-directional LSTM for no-reference video quality assessment (opens in a new tab)

  2. Source-code Summarization of Java Methods Using Control-Flow Graphs

    … to increase the prediction accuracy of a bi-directional long-short term memory (LSTM) source-code summarization model in terms of describing the functionality of Java methods. We use an attention-based bi-directional LSTM sequence-to-sequence model to show the use of linearized …

    sask Repository record for Source-code Summarization of Java Methods Using Control-Flow Graphs (opens in a new tab)

  3. Evaluation of machine learning classifiers in ordinal multiclass fake news detection scenario

    … due to variance in dataset labeling caused by ambiguity and subjectivity of semantic text. The LIAR Dataset was used in the experiments of this thesis. This dataset derived from PolitiFact fact-checking agency data which is composed of a 6-class ordinal labeling that places political statements …

    brazil-uerj Repository record for Evaluation of machine learning classifiers in ordinal multiclass fake news detection scenario (opens in a new tab)

  4. ResCoCo: Residual ConvLSTM Network with Contrastive Learning for 3D Joint Angle Estimation

    … angle, a Deep Learning approach, Residual ConvLSTM network with Contrastive Learning (ResCoCo), is proposed in this study. A sequence shortening layer is introduced in ResCoCo to discard part of the output sequence estimated by bi-directional LSTM layers from incomplete context, and a residual …

    mcmaster Repository record for ResCoCo: Residual ConvLSTM Network with Contrastive Learning for 3D Joint Angle Estimation (opens in a new tab)

  5. Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits

    Public vulnerability databases such as CVE and NVD account for only 60% of security vulnerabilities present in open-source projects and are known to suffer from inconsistent quality. Over the last two years, there has been considerable growth in the number of known vulnerabilities across projects …

    waterloo Repository record for Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits (opens in a new tab)

  6. Adversarial robustness of deep learning enabled industry 4.0 prognostics

    … learning algorithms are known for their susceptibility to adversarial examples. Such adversarial attacks have been extensively studied in the computer vision domain. However, it is surprising that their impact on the PHM domain is yet not explored. Thus, modern data-driven intelligent PHM systems …

    missouri Repository record for Adversarial robustness of deep learning enabled industry 4.0 prognostics (opens in a new tab)

  7. A Comprehensive Survey and Deep Learning-Based Prediction on G-quadruplex Formation and Biological Functions

    … structure and are involved in important biological processes at transcriptional and epigenetic levels. However, the underlying molecular mechanisms and locating of G4 still remain elusive due to the complexity of G4s. Taking advantage of the development of high-throughput sequencing …

    iupui Repository record for A Comprehensive Survey and Deep Learning-Based Prediction on G-quadruplex Formation and Biological Functions (opens in a new tab)

  8. Deep Reinforcement Learning in Natural Language Scenarios

    … policy in a dynamic environment. Recently, by combining deep learning with reinforcement learning, researchers have made significant breakthroughs in many artificial intelligence applications. The most notable applications are Atari games and game of Go. However, natural language applications …

    washington Repository record for Deep Reinforcement Learning in Natural Language Scenarios (opens in a new tab)

  9. Integrating Deep Learning and Network Science to Support Healthcare Management

    … documents, such as intellectual properties, biomedical research literature, and health social medial conversation, has grown rapidly in the last few years. The texts in the health domains are no longer being used only for storing data and conveying information for communication purposes but …

    arizona-thes Repository record for Integrating Deep Learning and Network Science to Support Healthcare Management (opens in a new tab)

  10. Low-power Artificial Intelligence of Things(AIoT) Systems

    … excellent innovation after the Internet and mobile networks in the information era, aiming at connecting billions of end-devices across scales. A multitude of IoT applications often operate under conditions of constrained energy resources, which has rendered low-power IoT systems a subject of …

    msu Repository record for Low-power Artificial Intelligence of Things(AIoT) Systems (opens in a new tab)

  11. Detecting Objects and Actions with Deep Learning

    … boxes. Finally, we present a multi-stream bi-directional recurrent neural network for action detection. This was the first deep learning based system which could perform action localization in long videos and it could do it just with RGB data, without requiring any skeletal models or …

    maryland Repository record for Detecting Objects and Actions with Deep Learning (opens in a new tab)

  12. A Deep Learning Approach to Predict Accident Occurrence Based on Traffic Dynamics

    … network model based on long short term memory (LSTM). We apply it to forecast the expected speed values on freeways’ links and identify the anomalies as potential accident occurrences. Several detailed features such as weather, traffic speed, and traffic flow of upstream and downstream points …

    vt Repository record for A Deep Learning Approach to Predict Accident Occurrence Based on Traffic Dynamics (opens in a new tab)