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 49 for “"Recurrent neural network (RNN)"”.
-
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 …
-
On the computational power of RNNs
Recent neural network architectures such as the basic recurrent neural network (RNN) and Gated Recurrent Unit (GRU) have gained prominence as end-to-end learning architectures for natural language processing tasks. But what is the computational power of such systems? We prove that finite precision …
-
Predicting football match outcomes with fantasy league data and deep learning
… used to predict the outcome of matches. We use a Recurrent Neural Network (RNN) with Gated Recurrent Unit (GRU) layers to predict the outcome of matches. Our combined method shows good results, improving significantly on state of the art.
-
Multi-character prediction using attention
… image is first passed through a Convolutional Neural Network (CNN) that serves as feature extractor. Then at each Recurrent Neural Network (RNN) time step, the attention mechanism attends to the relevant features sequentially to make predictions. The attention mechanism also includes a start …
-
A Framework for Analysis of Softball Pitching, as Applied to Legal and Illegal Pitches
… By developing a pose estimation algorithm and Recurrent Neural Network (RNN) for use on videos of real collegiate pitchers, we aim to distinguish physiological differences between these types of pitches and use our RNN to automatically detect illegal pitches. Our pose estimation results …
-
Joint spatial and layer attention for convolutional networks
… sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., “what” feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., “where”) to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a …
-
Multi-objective evolutionary neural architecture search for recurrent neural networks
Artificial neural network (ANN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of ANN architectures, and has proven to be successful in finding ANN architectures that can …
-
MACHINE LEARNING FOR CONSTITUTIVE MODELLING
… learning. For history dependent materials, the recurrent neural network (RNN) is adopted for the training of path dependent mechanical responses, due to its advanced learning ability for history dependent behavior. However, the huge data generation time of RNN surrogate model limits the off-line …
-
Two approaches to robust hand pose estimation : generative modeling and semantic relations
… We first investigate the use of segmentation networks within pose estimation pipelines with a focus on fine parts segmentation. We present two implementations of a novel method for fine parts segmentation employing a higher-order Conditional Random Field (CRF) that measures attachment and …
-
High-Dimensional Generative Models for 3D Perception
… feature encoder, and a generative Bayesian network. In the next section, a novel multi-level generative chaotic Recurrent Neural Network (RNN) has been proposed using a sparse tensor structure for image restoration. In the last part of the dissertation, we discuss the detection followed by …
-
INCORPORATING EMR AND GENOMIC DATA USING NLP AND MACHINE LEARNING TO REFINE CANCER TREATMENT
… extract NGS-related information. Three types of recurrent neural network (RNN), including gated recurrent unit (GRU), long-short term memory (LSTM), and bidirectional LSTM (LSTM_Bi), were applied to classify documents to treatment-change group and no-treatment-change group. The performances of …
-
Data-Driven Decoding of Quantum Surface Codes using Recurrent Neural Networks
… remains a significant challenge. In this thesis, neural network-based decoders are explored as an approach to decode QEC data. In particular, recurrent neural network (RNN) architectures, including Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), are investigated as their are able to …
-
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 …
-
Predicting blood pressure response to fluid bolus therapy in the ICU using attention-based stacked neural networks for clinical interpretability
… utilized regression models and attention-based recurrent neural network (RNN) algorithms to predict the response of hypotensive patients to FBT from a multi-clinical information system large-scale database. We investigated time-series modeling with the use of the stacked long short term memory …
-
Spiking Neural Network with Memristive Based Computing-In-Memory Circuits and Architecture
… There are two main types of Artificial Neural Networks (ANNs), Feedforward Neural Network (FNN) and Recurrent Neural Network (RNN). In this thesis we first study the types of RNNs and then move on to Spiking Neural Networks (SNNs). SNNs are an improved version of ANNs that mimic …
-
LSTM and extended dead reckoning automobile route prediction using smartphone sensors
… Illinois. The GPS data is used to train the LSTM neural network along with the thirty non-GPS features recorded from the smart-phone. The output is a route shape that is used to determine potential driving route and verify if a route input is correct. This method is evaluated against our …
-
Barometer-Based Tactile Sensing: Characterization, Processing, and Applications for Dynamic Manipulation
… Robotics Lab. Previous work demonstrated that neural networks could infer contact location and three-axis contact force from barometers embedded within an elastomer. However, these models did not account for the viscoelastic behavior of the elastomer, which degrades sensor repeatability and …
-
Spiking Neural Networks for Low-Power Medical Applications
… "spikes" instead of continuous values, spiking neural networks (SNN) may be the right model architecture to address these concerns. This work investigates the proposed advantages of SNNs compared to more traditional architectures when tested on various medical datasets. We compare the energy …
-
H2OGAN: A Deep Learning Approach for Detecting and Generating Cyber-Physical Anomalies
… WSSs. Proposing Water Generative Adversarial Networks, H2OGAN, a time-series GAN-based model designed to synthesize water data. H2OGAN produces water data based on the characteristics within the expected constraints of water data cardinality. This generative model serves multiple purposes, …
-
Integrating Transactive Energy and Machine Learning For Re-Energizing Wastewater Treatment Plants
… speed and power load forecasting. Particularly, recurrent neural network (RNN), long short-term memory (LSTM), and ensemble models are adopted as intelligent computing tool for generation forecasting. A regression model was developed to forecast the power output of onsite wind turbines. …
Page 1 of 3