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 94 for “"Recurrent networks"”.
-
Gated recurrent networks for scene parsing
… routing and gating mechanisms in deep neural networks for dense pixel labeling tasks including scene parsing and semantic segmentation. The goal of semantic segmentation is to label every pixel in an image or video frame according to a specific set of object classes while scene parsing …
-
Time series prediction using real-time recurrent networks
… Electrocardiogram (ECG) data by the Real-Time Recurrent Networks (RTRN). The RTRN models have been constructed using the Real-Time Recurrent Learning (RTRL) algorithm with teacher forcing. Both single-point prediction and multi-point prediction were used to forecast the ECG behaviors. The ECG …
-
Deep Recurrent Networks for Gesture Recognition and Synthesis
… in a variety of tasks. On the other hand, deep networks can be overwhelming to use for a majority of developers, requiring a lot of tuning and tweaking to work as expected. Additionally, these networks are infamous for their requirement for large amounts of training data, further hampering their …
-
APPLICATION OF RECURRENT NETWORKS FOR SPACECRAFT ATTITUDE CONTROL
… to be performed. An alternative is to use a recurrent neural network to solve the allocation problem. Implementation of a recurrent neural network can solve the pseudoinverse of the torque transformation matrix of a spacecraft’s momentum exchange devices. The recurrent neural network is shown …
-
Signal propagation in recurrent networks of mouse barrel cortex
… and system levels, activity within neuronal networks significantly impact neural processing. For example, there are spatiotemporal interactions (neural correlations) between responses of neurons within populations that could potentially impact signal representation and propagation. …
-
A Methodology for the Development of Recurrent Networks for Sequence Processing Tasks
Artificial neural networks are increasingly being used for dealing with real world applications. Many of these (e.g. speech recognition) are based on an ability to perform sequence processing. A class of artificial neural networks, known as recurrent networks, have architectures which incorporate …
-
Self-Supervised Video Representation Learning by Recurrent Networks and Frame Order Prediction
… learning relied on encoder-decoder style networks in an unsupervised fashion, which would take in a few frames at a time. Research in the field of self-supervised learning is growing, and has shown promising results on image-related tasks to both learn data representations as well as …
-
Information-based Analysis and Control of Recurrent Linear Networks and Recurrent Networks with Sigmoidal Nonlinearities
… interactions in the activation of complex networks, including those in the brain. In this regard, classical tools from control theory, including controllability analysis, have been used to assay the extent to which such networks might respond to their afferent inputs. However, for natural …
-
Cortex-inspired goal-directed recurrent networks for developmental visual attention and recognition with complex backgrounds
Thesis (Ph. D.)--Michigan State University. Computer Science, 2010
-
Hopf bifurcation as an activation function for complex recurrent neural networks: A feasibility study
The performance of complex recurrent networks heavily relies on the selection of an appropriate activation function. Some established activation functions, known to enhance complex-valued recurrent networks, are chosen based on specific network properties. Exploring alternative approaches to …
-
Recurrent neural networks and time series prediction
… an exploration of the dynamic behavior of small recurrent networks. Proofs are presented to show that fixed points and hmit cycles can be produced by small recurrent networks. As an apphcation. a network trziined to a noisy signal for which the clean signal was a sine wave produced good signal …
-
Oscillations and Gain Control in Sensory Systems
Sensory neurons assemble to form networks that process inputs coming from the senses. Through synaptic connections neurons interact and create complex dynamical states in response to these inputs. Networks with different connectivity patterns are thought to display different states and therefore …
-
Modelling divisive inhibition in the primary visual cortex from optogenetic circuit mapping data
<p>Recurrent networks are abundant in the neocortex and are recognised as a means of amplifying feedforward thalamic sensory inputs. However, when operating at high gain, which is necessary for this signal amplification, the standard recurrent network firing rate model suffers from increased …
-
Solar Wind and Geomagnetic Activity - Predictions Using Neural Networks
This thesis shows how artificial neural networks (ANNs) can be applied to predict geomagnetic activity from solar-wind data. It introduces and summarizes five papers where development of ANN models are reported, and where predictions of geomagnetic activity are discussed. The studies cover …
-
The role of spatiotemporal correlations in the encoding and retrieval of synaptic patterns by STDP in recurrent spiking networks
… information within and between cerebral cortical networks. It remains unclear, however, how temporal and spatial correlations of signals and ongoing background spiking activity interact with STDP mechanisms to give rise to long-term memory. A recent computational study by Davison and Fregnac …
-
Looking under the hood: visualizing what LSTMs learn
Recurrent Neural Networks (RNNs) such as Long Short Term Memory (LSTM) and Gated Recurrent Units (GRUs) have been successful in many applications involving sequential data. The success of these models lies in the complex feature representations they learn from the training data. One criteria to …
-
Extracting Symbolic Representations Learned by Neural Networks
Understanding what neural networks learn from training data is of great interest in data mining, data analysis, and critical applications, and in evaluating neural network models. Unfortunately, the product of neural network training is typically opaque matrices of floating point numbers that are …
Page 1 of 5