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 66 for “"Neural network learning"”.
-
Towards More Reliable Neural Network Learning Models
Ideally, when a neural network makes a wrong decision or encounters an out-of-distribution example, its predictive confidence should be as low as possible. Three primary contributions in this dissertation address this challenge. The first two contributions are new approaches to mitigate …
-
New computational and statistical characterizations of neural network learning
A foundational goal of machine learning theory is to characterize the inherent computational and statistical complexity of some of the most basic tasks in machine learning. In this thesis, we present new results concerning two such tasks in neural network learning and beyond. First, we study the …
-
Algorithm animation and its application to artificial neural network learning
… of algorithm, namely back-propagation artificial neural network learning. The work entailed developing a framework for profiling views according to attributes such as symmetry, regularity, complexity, etc. This framework was based on current research in graphical data analysis and perception and …
-
Neural Network Learning for Time-Series Predictions Using Constrained Formulations
… along with violation guided backpropagation to neural network learning for near noiseless time-series benchmarks, we achieve much improved prediction performance as compared to that of previous work, while using less parameters. For noisy time-series, such as financial time series, we have …
-
A 3D ray traced biological neural network learning model and applications
Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset. However, current transfer learning algorithms …
-
Deep neural network learning-based classifier design for big-data analytics
… and the second step is classification using deep neural networks (DNN).First, multi-step dimension-reduction approaches are developed where both linear and nonlinear relationships among dimensions are considered. The dimensions are first grouped, and each group is then transformed. These two …
-
Neuromorphic deep convolutional neural network learning systems for FPGA in real time
Deep Learning algorithms have become one of the best approaches for pattern recognition in several fields, including computer vision, speech recognition, natural language processing, and audio recognition, among others. In image vision, convolutional neural networks stand out, due to their …
-
Insights into neural network learning of structured models : optimization, architectures, and scientific surrogates
… Motivated by the increasing relevance of deep learning across scientific disciplines, this thesis investigates the interplay between neural network architecture, loss landscape geometry, and optimization in scientific machine learning. We analyze optimization of physics-informed neural networks …
-
Dirbtiniai neuroniniai tinklai žaidimuose /
… work the author analyzes the usage of artificial neural networks in games. The author also analyzes several models of artificial neural network learning, supervised learning and reinforcement learning, and compare their application for creating an artificial neural network, designed for games. …
-
Graph Neural Network and Phylogenetic Tree Construction
Deep Learning had been widely used in computational biology research in past few years. A great amount of deep learning methods were proposed to solve bioinformatics problems, such as gene function prediction, protein interaction classification, drug effects analysis, and so on; most of these …
-
ALGORITHMIC IMPROVEMENTS FOR DIFFERENTIALLY PRIVATE LEARNING
Neural networks enable powerful applications in healthcare, social media, and beyond. However, they risk exposing sensitive information when learning from private data. Differential privacy (DP) provides rigorous protection for learning algorithms, yet applying DP to neural network learning remains …
-
Backpropagation for Continuous Theta Neuron Networks
… tonic firing states, and more. Previous work on learning rules for networks of theta neurons includes the derivation of a spike-timing based backpropagation algorithm for multilayer feedforward networks. However, this learning rule is only applicable to a fixed number of spikes per neuron, and is …
-
Vaizdų atpažinimas ir apdorojimas taikant dirbtinius neuroninius tinklus /
Even though, today neural networks are pretty good at performing a lot of object detection tasks, the main problem still remains -- neural network learning. As computer hardware evolves and becomes faster, this problem can seem to be less and less important. However, one of the main tasks in the …
-
Investigação in silico do mecanismo de reorganização sináptica do sono. Um algoritmo para maximizar a capacidade computacional de redes neurais esparsas
… can bring advantages to artificial neural networks. This thesis aims to apply neurobiological sleep-dependent learning mechanisms to machine learning. For this, we carried a review of memory consolidation theories and the computational models that support these theories. Observing …
-
New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays
A new neural network learning algorithm, called the Umbrella Algorithm, is developed and analysed. Its generalization, which does not exhibit over-specialisation, is observed in the EXOR problem and in an artificial data discrimination (Toy Data) problem. The learning time is found to be about 1/15 …
-
Abstract pattern learning with neural networks for improved sequential modeling
Deep neural networks have been widely used for various applications and have produced state-of-the-art results in domains like speech recognition, machine translation, and image recognition. Despite the impressive successes achieved with deep neural networks, there has been an increasing awareness …
-
Constructive learning: inducing grammars and neural networks
… focuses on two important areas of machine learning research--regular grammar inference and constructive neural network learning algorithms;Regular grammar inference is the process of learning a target regular grammar or equivalently a deterministic finite state automaton (DFA) from labeled …
-
Mokymosi neuroniniuose tinkluose optimizavimas /
… to improve and optimise single-layer artificial neural network learning in solving the classification task. Tasks of classification type often occur in practice - medicine, army, security systems and other areas. Most often, artificial neural networks using machine learning are used to solve the …
-
PACKET FILTER APPROACH TO DETECT DENIAL OF SERVICE ATTACKS
… quantity of packets or connections to crash its network resources, bandwidth, equipment, or servers. Packet filtering methods are the most known way to prevent these attacks via identifying and blocking the spoofed attack from reaching its target. In this project, the extent of the DoS attacks …
Page 1 of 4