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 7 of 7 for “"TRAINING OF ARTIFICIAL NEURAL NETWORKS"”.
-
Swarm-based Algorithms for Neural Network Training
The main focus of this thesis is to compare the ability of various swarm intelligence algorithms when applied to the training of artificial neural networks. In order to compare the performance of the selected swarm intelligence algorithms both classification and regression datasets were chosen from …
-
Intrinsically Evolvable Artificial Neural Networks
<p>Dedicated hardware implementations of neural networks promise to provide faster, lower power operation when compared to software implementations executing on processors. Unfortunately, most custom hardware implementations do not support intrinsic training of these networks on-chip. The training …
-
Aplicações de IA na sintonia de controladores PI e PID
PID controllers are present in approximately 96% of industrial control loops, yet it is estimated that a large portion of these controllers are not adequately tuned. Nowadays, tuning controllers using classic techniques is still a challenging task, which has motivated the development of new tools, …
-
Evolving Artificial Neural Networks using Cartesian Genetic Programming
NeuroEvolution is the application of Evolutionary Algorithms to the training of Artificial Neural Networks. NeuroEvolution is thought to possess many benefits over traditional training methods including: the ability to train recurrent network structures, the capability to adapt network topology, …
-
Computationally Intensive Design of Water Distribution Systems
The burdensome capital cost of urban water distribution systems demands the use of efficient optimization methods capable of finding a relatively inexpensive design that guarantees a minimum functionality under all conditions of operation. The combinatorial and nonlinear nature of the optimization …
-
Non-Parametric Probabilistic Anomaly Detection in Evolving Data: Applications to Time Series
This thesis examines the problem of anomaly detection in evolving data. Data-driven anomaly detection methods typically build a model for the normal behavior of the target system and score each data instance with respect to this model. A threshold is invariably needed to identify data instances …
-
ΤΕΧΝΗΤΑ ΝΕΥΡΩΝΙΚΑ ΔΙΚΤΥΑ ΓΙΑ ΥΛΟΠΟΙΗΣΗ ΣΥΣΤΗΜΑΤΩΝ ΥΠΟΣΤΗΡΙΞΗΣ ΑΠΟΦΑΣΕΩΝ
A NOVEL DECISION SUPPORT SYSTEM OF MOLECULAR STRUCTURE IS PROPOSED WHICH IS DEVELOPED ON A BASIS OF A COMPOSITION OF ARTIFICIAL NETWORK (AANS) AND IS APPLIED ON RESEARCH AREAS WHERE HUMAN EXPERIENCE IS EMLPOYED FOR THE PROMOTION OF DECISIONS. THE ARCHITECTURE OF THIS SYSTEM CAN BE ADAPTED ONTO THE …