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 156 for “"Recurrent Neural Network"”.
-
Higher Order Recurrent Neural Network for Language Modeling
In this thesis, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all recurrently fed to the hidden layers as feedback through …
-
Lipreading with convolutional and recurrent neural network models
… by a talking head, given only the video using neural network classification models. Two neural network architectures are developed and tested on the AVICAR dataset, including one convolutional neural network (CNN) model with fully connected classification layer, and one recurrent neural network …
-
Recurrent Neural Network Language Generation for Dialogue Systems
… proposed in this thesis. The model leverages a Recurrent Neural Network (RNN)-based surface realiser and a gating mechanism applied to input semantics. The model is motivated by the Long-Short Term Memory (LSTM) network. The RNN-based surface realiser and gating mechanism use a neural network to …
-
Recursive backpropagation algorithm applied to a globally recurrent neural network
In general, recursive neural networks can yield a smaller structure than purely feedforward neural network in the same way infinite impulse response (IIR) filters can replace longer finite impulse response (FIR) filters. This thesis presents a new adaptive algorithm that trains recursive neural …
-
Recurrent neural network language models in the context of under-resourced South African languages
Over the past five years neural network models have been successful across a range of computational linguistic tasks. However, these triumphs have been concentrated in languages with significant resources such as large datasets. Thus, many languages, which are commonly referred to as …
-
Wind Speed Forecasting for Power Generation Using a Self-Assembling Closed-Loop Recurrent Neural Network
This thesis presents the self-assembling recurrent neural network, SFA (Sequential Function Approximation), as a time series forecasting method for wind speed prediction. We compare its multi-step prediction performance against a proven recurrent neural network, NARX (Non-linear Auto-Regressive …
-
Supporting word learning with language-internal distributional statistics: A place for the recurrent neural network language model?
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-05-01
-
Experiencing language in the order that children do: Training on age-ordered child-directed speech facilitates semantic category learning in a recurrent neural network
Previous work has shown that semantic category knowledge can be captured by a distributional learning algorithm operating over naturalistic, noisy child-directed speech (Huebner & Willits, 2018). In chapter 1 of this work, I discuss the algorithm behind this study, and its ability to represent …
-
RNN-Based Generation of Polyphonic Music and Jazz Improvisation
… novel data sources and the character-based recurrent neural network architecture <em>char-rnn</em>. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.</p>
-
Sentiment Analysis Using Deep Learning: A Comparison Between Chinese And English
… dependencies. So, we propose a model based on recurrent neural network model using a context vector space model. Chinese information entropy is typically higher than English, we therefore hypothesise that context vector space model can be used to improve the accuracy of sentiment analysis. Our …
-
A Bi-Encoder LSTM Model for Learning Unstructured Dialogs
… presents a Long Short Term Memory (LSTM) based Recurrent Neural Network architecture that learns unstructured multi-turn dialogs and provides implementation results on the task of selecting the best response from a collection of given responses. Ubuntu Dialog Corpus Version 2 (UDCv2) was used as …
-
Lietuvių kalbos teksto atpažinimas /
This paper reviews convolutional and recurrent neural networks and their layers. Two models of handwritten Lithuanian text recognition are analyzed: convolutional recurrent neural network and ResNet-50. Convolutional recurrent neural network model is adapted to recognize Lithuanian words with the …
-
Data driven learning for feature binding and perceptual grouping with the Competitive Layer Model
… between elementary data structures in a recurrent neural network architecture, the so called Competitive Layer Model (CLM). The main result of the work is the development of an automatic learning method which extracts suitable interaction patterns from exemplary target groupings.
-
Characteristics of different deep neural networks and application of pre-trained model without transfer learning
Deep neural networks have been successful in many areas, some of them even surpass human performances. The goal of this thesis is using data simulations to present different characteristics of three deep neural networks: fully connected deep neural network, convolutional neural network, recurrent …
-
Long short-term memory recurrent neural networks for classification of acute hypotensive episodes
… evaluation of a series of Long short-term memory recurrent neural network (LSTM RNN) models which predict whether a patient will experience an AHE or not based on a time series of mean arterial blood pressure (ABP). A 2-layer, 128-hidden unit LSTM RNN trained with rmsprop and dropout …
-
Applying Neural Networks for Tire Pressure Monitoring Systems
… monitoring system is developed using neural net- works to identify the tire pressure of a vehicle tire. A quarter-car model was developed with Matlab and Simulink to generate simulated accelerometer output data. Simulation data are used to train and evaluate a recurrent neural network …
-
Investigations into controllers for adaptive autonomous agents based on artificial neural networks.
… of adaptive behaviour based on artificial neural networks. There are two distinct levels of enquiry. At the primary level, the initial aim was to design and implement a unified architecture integrating sensorimotor learning and overall control. This was intended to overcome shortcomings of …
-
Interdisciplinary Studies of Complex Network and Machine Learning and Its Applications
… this dissertation, we introduce the concept of network-based statistical inference methods of two types: network structure inference and variable inference. For network structure inference, we introduce correlation matrix, graphical Lasso, network clustering and identify the influencer in the …
-
Information fusion for an unmanned underwater vehicle through probabilistic prediction and optimal matching
… lag between AIS and sonar data collection. A recurrent neural network predicts a contact's future occupancy grid from a segment of its AIS track. Assignment costs are formed by comparing a sonar position with the predicted occupancy grids of relevant vessels. The assignment problem is solved …
-
Modeling repairable system failure data using NHPP reliability growth mode.
… for goodness-of-fit. The Weibull Time to Failure recurrent neural network (WTTE-RNN) framework, a probabilistic deep learning model for failure data, is also explored. However, we find that the WTTE-RNN framework is only appropriate failure data with independent and identically distributed …
Page 1 of 8