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 20 of 242 for “"RNNs"”.

  1. Financial time series forecasting via RNNs and Wavelet Analysis

    Recent successes in both Artificial Neural Networks (ANN) and wavelets have placed these two methods in the spotlight of quantitative traders seeking the best tool to forecast financial time series. The Wavelet Neural Network (W-NN), a prediction model which combines wavelet-based denoising and …

    rice Repository record for Financial time series forecasting via RNNs and Wavelet Analysis (opens in a new tab)

  2. Modelling temporal context for traffic light recognition using RNNs

    Abstract The purpose of this thesis is to investigate whether or not including temporal context using recurrent neural networks in real-time object detection systems can improve detection performance in traffic light recognition. This was investigated using the DriveU traffic light dataset. Two …

    chalmers Repository record for Modelling temporal context for traffic light recognition using RNNs (opens in a new tab)

  3. Genre Prediction Using RNNs And LLM-Enhanced Video Game Review Data

    … various information from the raw data and train RNNs (Recurrent Neural Networks) to predict a single genre of the games, "RPG" (Role-Playing Game). We then evaluate performance of the trained RNN models on the raw data, checking for generalizability and performance loss/improvement. Results are …

    arkansas Repository record for Genre Prediction Using RNNs And LLM-Enhanced Video Game Review Data (opens in a new tab)

  4. Incorporating neighbourhood features in RNNs for popularity forecasting for emerging research fields

    The accurate modelling and forecasting of the popularity of emerging fields can benefit researchers by allocating resources and efforts on promising research directions. While existing forecasting approaches enjoy various levels of success, most suffer from at least one of the following three …

    unsw Repository record for Incorporating neighbourhood features in RNNs for popularity forecasting for emerging research fields (opens in a new tab)

  5. What Really Counts: Theoretical and Practical Aspects of Counting Behaviour in Simple RNNs

    Recurrent Neural Networks (RNNs) are commonly used in sequential tasks and have been shown to be Turing complete, and are therefore theoretically capable of computing any task if the correct configuration is used. However, there is a long standing debate on the systematicity of NN learning. There …

    city-london Download PDF for What Really Counts: Theoretical and Practical Aspects of Counting Behaviour in Simple RNNs (opens in a new tab)

  6. Training Recurrent Neural Networks

    Recurrent Neural Networks (RNNs) are powerful sequence models that were believed to be difficult to train, and as a result they were rarely used in machine learning applications. This thesis presents methods that overcome the difficulty of training RNNs, and applications of RNNs to challenging …

    toronto-retro Repository record for Training Recurrent Neural Networks (opens in a new tab)

  7. Higher Order Recurrent Neural Network for Language Modeling

    … preceding states in recurrent neural networks (RNNs), which are all recurrently fed to the hidden layers as feedback through different weighted paths. By extending the popular recurrent structure in RNNs, we provide the models with better short-term memory mechanism to learn long term dependency …

    york Repository record for Higher Order Recurrent Neural Network for Language Modeling (opens in a new tab)

  8. Near-Time Predictions of Future Truck Locations

    … vehicle using Recurrent Neural Networks (RNNs) and its different variants (a time-series approach). In addition, we discuss the required data pre-processing steps, the architecture of RNNs and the experiments to compare the different variants of RNNs. These experiments show that Long …

    chalmers Repository record for Near-Time Predictions of Future Truck Locations (opens in a new tab)

  9. Target Propagation in Recurrent Neural Networks

    Recurrent Neural Networks (RNNs) are a type of artificial neural network designed to process sequential data and model temporal relationships. This makes them essential for tasks like natural language processing, speech recognition, and time- series prediction. They remain relevant because of their …

    kings Repository record for Target Propagation in Recurrent Neural Networks (opens in a new tab) Download PDF for Target Propagation in Recurrent Neural Networks (opens in a new tab)

  10. Using Recurrent Neural Networks to Code Interviewer Question-Asking Behaviors: A Proof of Concept

    … automated by Recurrent Neural Networks (RNNs; a machine learning technique that can learn to categorize sequential data using patterns learned from previously categorized examples), saving time and money. Humans use transcripts from 33 questions in the Work and Leisure Today II telephone …

    nebraska Repository record for Using Recurrent Neural Networks to Code Interviewer Question-Asking Behaviors: A Proof of Concept (opens in a new tab)

  11. Energy-Efficient Recurrent Neural Network Accelerators for Real-Time Inference

    … as speech recognition and machine translation. RNNs are difficult to compute because of their massive arithmetic operations and large memory footprint. RNN inference workloads used to be executed on conventional general-purpose processors including Central Processing Units (CPU) and Graphics …

    zurich

  12. Using Long-Short-Term-Memory Recurrent Neural Networks To Predict Aviation Engine Vibrations

    … flights that suffered from excessive vibration. RNNs can provide a more generalizable and robust method for prediction over analytical calculations of engine vibration, as analytical calculations must be solved iteratively based on specific empirical engine parameters, and this database contains …

    nodak Repository record for Using Long-Short-Term-Memory Recurrent Neural Networks To Predict Aviation Engine Vibrations (opens in a new tab)

  13. Comparative Analysis of Different Machine Learning Techniques for Hypertrophic Cardiomyopathy Detection Using ECG Data

    … (RF) classifier and Recurrent Neural Networks (RNNs), for HCM detection using Electrocardiogram (ECG) data. Using a dataset comprising ECG recordings from patients with and without HCM, we extracted relevant features to train and evaluate the performance of different classifiers and RNN models. …

    buffalo Repository record for Comparative Analysis of Different Machine Learning Techniques for Hypertrophic Cardiomyopathy Detection Using ECG Data (opens in a new tab)

  14. Interpretation and Optimization of Recurrent Neural Network Performance Through Lyapunov Exponents Methodology

    … over long time-sequences can make training RNNs particularly challenging and difficult to interpret. The hidden states of RNNs can be viewed as non-autonomous dynamical systems which can be analyzed using dynamical systems tools. In this work, we leverage Lyapunov Exponents, a dynamical …

    washington Repository record for Interpretation and Optimization of Recurrent Neural Network Performance Through Lyapunov Exponents Methodology (opens in a new tab)

  15. Solutions of linear equations and a class of nonlinear equations using recurrent neural networks

    … (the human brain). Recurrent neural networks (RNNs) are characterized by neuron connections which include feedback paths. This dissertation uses the dynamics of RNN architectures for solving linear and certain nonlinear equations. Neural network with linear dynamics (variants of the well-known …

    portland-state Repository record for Solutions of linear equations and a class of nonlinear equations using recurrent neural networks (opens in a new tab)

  16. Improving Time Series Prediction using Recurrent Neural Networks and Evolutionary Algorithms

    … In this thesis, recurrent neural networks (RNNs), trained with an evolutionary algorithm (EA) have been used instead. RNNs can have short-term memory and the EA has the advantage that it affects the architecture of the networks and not only the weights. However, the RNNs are often hard to …

    chalmers Repository record for Improving Time Series Prediction using Recurrent Neural Networks and Evolutionary Algorithms (opens in a new tab)

  17. Exploring many-body Physics with Recurrent Neural Networks

    … processing community, Recurrent neural networks (RNNs) have enabled remarkable progress in speech recognition and machine translation. These architectures belong to the class of autoregressive generative models which allow for exact likelihood estimation and for a perfect sampling of multi-modal …

    waterloo Repository record for Exploring many-body Physics with Recurrent Neural Networks (opens in a new tab)

  18. Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks

    … analysis reveals new interpretations of how RNNs implement hierarchical priors during the language recognition task. Overall, the results suggest a strong structural relationship between internal representations used by RNNs and fnite automata, and explain the well-known ability of RNNs to …

    rice Repository record for Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks (opens in a new tab)

  19. Energy efficient, secure and noise robust deep learning for the internet of things

    … networks (CNNs) and recurrent neural networks (RNNs). For CNNs, the work proposes dynamic precision scaling algorithm, and precision flexible computing unit to accelerate CNNs training. For RNNs, the work studies impact of various hyper-parameters to enable low precision training of RNNs and …

    gatech Repository record for Energy efficient, secure and noise robust deep learning for the internet of things (opens in a new tab)

  20. Identification of locust neuronal systems with recurrent neural networks

    … of ANNs called Recurrent Neural Networks (RNNs) for modelling time-series datasets derived from neuronal systems.<br/><br/>In achieving this objective, this thesis investigates the efficacy of RNNs in modelling a series of neurons in the locust hind leg. First, the graded potentials of locust …

    soton Download PDF for Identification of locust neuronal systems with recurrent neural networks (opens in a new tab)

Page 1 of 13