351 |
Νευρωνικά δίκτυα: αρχιτεκτονική και εφαρμογέςΓεωργάνα, Αθηνά 26 June 2008 (has links)
Μια σύντομη αναφορά σε κάποια γνωστά μοντέλα Νευρωνικών Δικτύων, περιγραφή της αρχιτεκτονικής τους και εφαρμογές. Παραδείγματα και εφαρμογές Δυναμικών Νευρωνικών Δικτύων. Γενικό πλαίσιο λειτουργίας των CNN, ιδιότητες και εφαρμογές. / A short reference in Neural Networks, architecture description and applications. Implementation of Dynamic Neural Networks. CNN (cellular neural networks) paradigm, attributes and examples.
|
352 |
Υπολογιστική νοημοσύνη και ομαδοποίησηΚανδηλιώτης, Στέφανος 17 September 2008 (has links)
Η εργασία ασχολείται με την ομαδοποίηση δεδομένων ανθρώπινου γονιδιόματος με την χρήση αλγόριθμων ομαδοποίοησης και νευρωνικών δικτύων για τον διαχωρισμό του δείγματος σε ομάδες με βάση το αν έχουν κάποιο είδος ασθένειας ή όχι ή για τον καθορισμό του τύπου της ασθένειας. Παρουσιάζονται κάποια πειράματα που έγιναν με την χρήση και των δύο μεθόδων. / This master thesis is an application of clustering algorithms and artificial neural networks on human dna data in order to cluster the data in groups depending on wether a person has or hasn't an illness or what type of ilness one has. The thesis shows the results of some experiments conducted using either technique (clustering, ANNs) and a combination of both.
|
353 |
Robust Visual Recognition Using Multilayer Generative Neural NetworksTang, Yichuan January 2010 (has links)
Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However, they are not robust to common variations such as occlusion and random noise. In this thesis, we explore two strategies for improving the robustness of DBNs. First, we show that a DBN with sparse connections in the first layer is more robust to variations that are not in the training set. Second, we develop a probabilistic denoising algorithm to determine a subset of the hidden layer nodes to unclamp. We show that this can be applied to any feedforward network classifier with localized first layer connections. By utilizing the already available generative model for denoising prior to recognition, we show significantly better performance over the standard DBN implementations for various sources of noise on the standard and Variations MNIST databases.
|
354 |
Controllability and applications of CNNLara, Teodoro 12 1900 (has links)
No description available.
|
355 |
Transient Mixed Synapses Regulate Emerging Connectivity in Simple Neuronal NetworksRichardson, Jarret Keith 16 December 2013 (has links)
The electrical synapse was first described over 50 years ago. Since that time appreciation of its complexity and importance has grown, including the hypothesis that early transient formation of these synapses is important to adult patterns of connectivity in neural networks. Presented in this dissertation are studies utilizing identified neurons in cell culture from the snail Helisoma trivolvis to examine discrete periods of electrical synapse formation during regeneration with sustained or transient expression. Extensive knowledge of connectivity patterns of the buccal neurons of Helisoma in cell culture and the ganglia, provide a useful framework for looking at modulation and manipulation of electrical synapses and their impact and emerging connectivity in a simple neuronal network.
Two types of electrical connections were observed those that were transient, between a B19 and a B110 and those that were sustained, between a B19 and another B19. Dopamine (DA) modulation of forming electrical synapses (FES) produces a synapse specific effect at those either destined to be transient (TES) or sustained (SES) and may be a direct effect on the gap junctions at the synapses, as is the case at TES, or an indirect effect on other membrane currents, as seen in SES. DA modulation produces different outcomes at SES-centered networks and TES-centered networks with respect to new chemical synapse formation, demonstrating network-dependent effects of electrical synapse modulation.
Pharmacological blockade of chemical and electrical components at forming mixed synapses in some cases alters subsequent synapse formation although due to the variable nature does not appear to be a direct interaction between chemical and electrical synapses. Three-cell networks appear to display a balancing mechanism for overall electrical coupling when electrical synapses are blocked suggesting a competition for some resource in the construction or trafficking of gap junctions. In addition to electrophysiological examinations, network coupling can be assessed utilizing fluorescent calcium imaging to look at coincidence of calcium changes as an output for coupling between cells. This technique provides a useful tool for less invasive studies of neuronal networks and the impact of coupling at mixed synapses.
|
356 |
Neural networks modelling of stream nitrogen using remote sensing information: model development and applicationLi, Xiangfei Unknown Date
No description available.
|
357 |
Modelling motor cortex using neural network control lawsLillicrap, Timothy Paul 31 January 2014 (has links)
The ease with which our brains learn to control our bodies belies intricate neural processing
which remains poorly understood. We know that a network of brain regions
work together in a carefully coordinated fashion to allow us to move from one place
to another. In mammals, we know that the motor cortex plays a central role in this
process, but precisely how its activity contributes to control is a matter of long and
continued debate. In this thesis we demonstrate the need for developing mechanistic
neural network models to address this question. Using such models, we show that contentious
response properties of non-human primate primary motor cortex (M1) neurons
can be understood as reflecting control processes which take into account the physics
of the body. And we develop new computational techniques for teaching neural network
models how to execute control. In the first study (Chapter 2), we critically examined a
recently developed correlation-based descriptive model for characterizing the activity
of M1 neuron activity. In the second study (Chapter 3), we developed neural network
control laws which performed reaching and postural tasks using a physics model of
the upper limb. We show that the population of artificial neurons in these networks exhibit
preferences for certain directions of movement and certain forces applied during
posture. These patterns parallel empirical observations in M1, and the model shows
that the patterns reflect particular features of the biomechanics of the arm. The final
study (Chapter 4) develops new techniques for building network models. To understand
how the brain solves difficult control tasks we need to be able to construct mechanistic
models which can do the same. And, we need to be able to construct controllers that
compute via simple neuron-like units. In this study, we combine tools for automatic computation
of derivatives with recently developed ideas about second-order approaches
to optimization to build better neural network control laws. Taken together, this thesis
helps develop arguments for, and the tools to build mechanistic neural network models
to understand how motor cortex contributes to control of the body. / Thesis (Ph.D, Neuroscience) -- Queen's University, 2014-01-31 10:34:43.816
|
358 |
Toward a formalism for the automation of neural network construction and processing controlCzuchry, Andrew J., Jr. 08 1900 (has links)
No description available.
|
359 |
Nonlinear flight control using neural networksKim, Byoung Soo 12 1900 (has links)
No description available.
|
360 |
Damage detection and health monitoring of structures using dynamic response and neural network techniquesLuo, Huageng 08 1900 (has links)
No description available.
|
Page generated in 0.0544 seconds