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 84 for “"Recurrent Network"”.
-
An Inhibitory Recurrent Network in the Olfactory System
Neuromodulatory circuits are a necessary component of neural flexibility as they are able to act differentially depending on the receptors expressed by their downstream targets. Identifying the synaptic partners of modulatory neurons and determining the neurotransmitter and receptor content of …
-
SalAR: Attentive recurrent network for dynamic visual saliency
… domains of computer vision to build a static network architecture. As gaze is usually fixated on objects encoded in image classification networks, we design our model by extending the VGG-16 network. We present comprehensive quantitative and qualitative analysis on three large-scale video …
-
Single channel speech enhancement with residual learning and recurrent network
… our work, we propose a speech de-noising neural network adopting multiple time-frames to multiple time-frames approach, aiming to greatly reduce computation burden for real-world applications as well as maintain decent speech quality. In this paper, we propose two neural networks, namely ResSE …
-
On the effect of dynamic adjustment of recurrent network parameters on learning
… thesis examines sequential learning in a neural network model derived by M. I. Jordan and J. L. Elman. In each of three experiments, different network parameters are systematically altered in a series of simulations. Each simulation measures learning ability for a specific network configuration. …
-
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 …
-
Hebbian learning in recurrent neural networks for natural language processing
… research project examines Hebbian learning in recurrent neural networks for natural language processing and attempts to interpret language at the level of a two and one half year old child. In this project five neural networks were built to interpret natural language: a Simple Recurrent Network …
-
Advanced architecture and training algorithms for recurrent neural networks
"Recurrent neural networks (RNN) attract considerable interest in computational intelligence fields because of their superior power in processing spatio-temporal data and time-varying signals. Traditionally, the recurrency of a neural network occurs between input samples along the time axis. The …
-
Žmogaus judėjimo generavimas naudojant neuroninius tinklus /
… These methods are based on convolutional and recurrent neural networks. In order to compare them quantitatively, a new metric is proposed, the results of which are then compared to a conducted user survey. Finally, some improvements on configuration on the best performing recurrent network are …
-
Information-geometric method for multiple neuronal spike data analysis
… were conducted based on simplified neural network structure, which has limitations in the real brain. We systematically extended the previous studies by using intensive mathematical analysis and numerical simulations of realistic and complex neural network. The studies show that information …
-
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 …
-
Understanding the Role of Dynamics in Brain Networks: Methods, Theory and Application
The brain is inherently a dynamical system whose networks interact at multiple spatial and temporal scales. Understanding the functional role of these dynamic interactions is a fundamental question in neuroscience. In this research, we approach this question through the development of new methods …
-
Dynamics of phase locking in neuronal networks in the presence of synaptic plasticity
The behavior generated by neuronal networks depends on the phase relationships of its individual neurons. Observed phases result from the combined effects of individual cells and synaptic connections whose properties change dynamically. The properties of individual cells and synapses can often be …
-
A biologically plausible sparse approximation solver on neuromorphic hardware
… and the ability to accurately implement a recurrent network on the TrueNorth chip. Our design methodology offers the foundation for low-power embedded systems signal processing applications using the TrueNorth chip.
-
Μελέτη των μηχανισμών διατάραξης της ομαλής κυτταρικής λειτουργίας μέσω της ανακατασκευής γονιδιακών ρυθμιστικών δικτύων
… was the reconstruction of gene regulatory networks (GRN) based on that we develop and implemented a euro fuzzy recurrent network (NFRN). NFRN was used to predict time series of microarray gene expression data. The prediction in NFRN is accomplished through fuzzy rules. Finally the …
-
Dynamics analysis and applications of neural networks
… analysis and applications of feed-forward neural networks, recurrent networks with saturating transfer functions and with nonsaturating transfer functions. To overcome sensitivity and slow learning of conventional back-propagation algorithm, a new training algorithm for multilayer feed-forward …
-
Cognitive Learning and Memory Systems Using Spiking Neural Networks
Neural networks have been studied for many years to mimic biological neural systems. However, humans can thoroughly defeat artificial intelligence with little difficulty when facing with cognitive tasks. The goal of this thesis is to investigate aspects of theories of spiking neural networks in an …
-
FACIAL LANDMARK DETECTION TOWARDS ROBUSTNESS
… on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures is then developed for landmark detection under challenging unconstrained conditions and outperforms the existing state-of-the-art methods. To further enhance our model's capability …
-
Recurrent Neural Networks and Matrix Methods for Cognitive Radio Spectrum Prediction and Security
In this work, machine learning tools, including recurrent neural networks (RNNs), matrix completion, and non-negative matrix factorization (NMF), are used for cognitive radio problems. Specifically addressed are a missing data problem and a blind signal separation problem. A specialized RNN called …
-
Heavy vehicle path control with neural networks - Heavy vehicle path control with neural networks
… thesis explores the possibility of using neural networks for solving the path control problem, i.e. how to follow a predefined path as closely as possible. Two main approaches are used to achieve this, namely supervised learning and reinforcement learning. The supervised learning approach is …
Page 1 of 5