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 57 for “"training algorithm"”.
-
A comparative study of neural network algorithms.
… forward neural network is trained using a Fast training algorithm. Then the fast training algorithm is compared with the delta rule training algorithm. The various neural network models studied in this thesis are Hopfield, Hamming, Carpenter/Grssberg, Kohonen, Single layer and Multi-layer neural …
-
Multiple aspect ranking for opinion analysis
… scores, one for each aspect. We present an algorithm that jointly learns ranking models for individual aspects by modeling the dependencies between assigned ranks. This algorithm guides the prediction of individual rankers by analyzing meta-relations between opinions, such as agreement and …
-
Development of self-adaptive back propagation and derivative free training algorithms in artificial neural networks
… dynamically self-adaptive, derivative-free and training parameter free artificial neural network (ANN) training algorithms are developed. They are defined as self-adaptive back propagation, multi-directional and restart ANN training algorithms. The descent direction in self-adaptive back …
-
Design methodology for a neural network-based telemetry monitor
… into this framework are a newly developed training algorithm and the concept of cooperative network architectures. The feasibility of such an approach is assessed for its ability to identify faults in low frequency waveforms and to generate subsequent controlling outputs for a single …
-
On Principled Modeling of Inductive Bias in Machine Learning
The inductive bias of a learning algorithm is the set of assumptions that the hypothesis uses to predict unseen data, governing its generalization power. This thesis focuses on principled approaches to modeling inductive bias of learning algorithms. We start with a unifying view on inductive bias …
-
Active disturbance cancellation in nonlinear dynamical systems using neural networks
… presented. Appropriate modifications to the CMAC training algorithm are derived which allow convergent adaptation for a variety of secondary signal paths. Analytical bounds on the maximum learning gain are presented which guarantee convergence of the algorithm and provide insight into the …
-
A Study on Deep Learning: Training, Models and Applications
… hardware like high performance GPUs, training deep models, such as fully-connected deep neural networks (DNNs) and convolutional neural networks (CNNs), from scratch becomes practical, and using well-trained deep models to deal with real-world large scale problems also becomes …
-
A radial basis function approach to pricing and hedging options incorporating transaction costs
… will adopt McLoone's hybrid linear/nonlinear training algorithm in developing RBF network models for the purpose of pricing and hedging options. An empirical study was first conducted to determine the suitability of our RBF network models in recovering simulated Black-Scholes option prices. We …
-
Environmental curriculum learning for efficiently achieving superhuman play in games
Reinforcement learning has made large strides in training agents to play games, including complex ones such as arcade game Pommerman and real-time strategy game StarCraft II. To allow agents to grasp the many concepts in these games, curriculum learning has been used to teach agents multiple skills …
-
Discrete HMM isolated digit recognition
This research develops an algorithm to perform isolated word recognition. A detailed description of the recognition system is presented in this thesis. We discuss detection of a spoken word from a recording using an end-point algorithm, extraction of the feature vectors from the sampled speech …
-
Sparse modeling of high-dimensional data for learning and vision
… prediction accuracy. Experiments show that the algorithm leads to surprisingly good results. Graph construction is critical for those graph-orientated algorithms designed for the purposes of data clustering, subspace learning, and semi-supervised learning. We model the graph construction …
-
An Enhanced Learning for Restricted Hopfield Networks
This research investigates developing a training method for Restricted Hopfield Network (RHN) which is a subcategory of Hopfield Networks. Hopfield Networks are recurrent neural networks proposed in 1982 by John Hopfield. They are useful for different applications such as pattern restoration, …
-
A color identification system based on class-oriented adaptive color space quantization
… and is integrated with a supervised training algorithm. From a set of training samples, a partition of the original RGB color space is determined, based on the intersection of meaningful parametric descriptions of the classes. Color histograms are constructed relative to the resulting …
-
The role of dynamic features in speaker verification
… that the priority of the maximum likelihood training algorithm is to model stationary regions, and the role of dynamic features in GMM system, is to ensure that the classification focuses on static regions rather than to model dynamics. Study on TI-SV was carried out using conventional GMMs. …
-
Devices and Algorithms for Analog Deep Learning
… practical implementation: devices satisfying algorithm-imposed requirements and algorithms running on nonideality-tolerant routines. This thesis demonstrates a near-ideal device technology and a superior neural network training algorithm that can ultimately propel analog computing when …
-
Data Centric Defenses for Privacy Attacks
Recent research shows that machine learning algorithms are highly susceptible to attacks trying to extract sensitive information about the data used in model training. These attacks called privacy attacks, exploit the model training process. Contemporary defense techniques make alterations to the …
-
An Experimental and Theoretical Study of Pile Foundations Embedded in Sand Soil
… self-tuning supervised Levenberg-Marquardt (LM) training algorithm, based on a MATLAB environment, was introduced and applied in this process. The proposed algorithm was trained after conducting a comprehensive statistical analysis, the key objectives being to identify and yield reliable …
-
Accelerating distributed neural network training with network-centric approach
Distributed training of Deep Neural Networks (DNN) is an important technique to reduce the training time of large DNNs for a wide range of applications. In existing distributed training approaches, however, the communication time to periodically exchange parameters (i.e., weights) and gradients …
-
Design of Deep Neural Networks Formulated as Optimisation Problems
… of network architecture as well as the training of the network weights. Each process can be formulated into an optimisation algorithm and can be investigated with regard to optimisation performance. The training of the network weights is defined as a minimisation of the objective …
Page 1 of 3