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 13 of 13 for “"neuroevolution"”.
-
Optimising the Optimiser: Meta NeuroEvolution for Artificial Intelligence Problems
Since reinforcement learning algorithms have to fully solve a task in order to evaluate a set of hyperparameter values, conventional hyperparameter tuning methods can be highly sample inefficient and computationally expensive. Many widely used reinforcement learning architectures originate from …
-
NEUROEVOLUTION AND AN APPLICATION OF AN AGENT BASED MODEL FOR FINANCIAL MARKET
<p>Market prediction is one of the most difficult problems for the machine learning community. Even though, successful trading strategies can be found for the training data using various optimization methods, these strategies usually do not perform well on the test data as expected. Therefore, …
-
Efficient Multi-Objective NeuroEvolution in Computer Vision and Applications for Threat Identification
… two new models, a practical Multi-Objective Neuroevolutionary approach for Convolutional Autoencoders (MONCAE, Chapter 3) and a Resource-Aware model for Multi-Objective Semantic Segmentation (RAMOSS, Chapter 4). Interestingly, these ap- proaches reached state-of-the-art results using a …
-
Worldwide Infrastructure for Neuroevolution: A Modular Library to Turn Any Evolutionary Domain into an Online Interactive Platform
… framework, called Worldwide Infrastructure for Neuroevolution (WIN), exploits an important unifying principle among all evolutionary algorithms: regardless of the overall methods and parameters of the evolutionary experiment, every individual created has an explicit parent-child relationship, …
-
Evolutionary Design of Artificial Neural Networks Using a Descriptive Encoding Language
… neural networks by evolutionary algorithms (neuroevolution) has generated much recent research both because successful approaches will facilitate wide-spread use of intelligent systems based on neural networks, and because it will shed light on our understanding of how "real" neural networks …
-
Smarter NEAT Nets
… of a ge- netic neural net algorithm called NEAT (NeuroEvolution of Augmenting Topolo- gies). The modification aims to accomplish its goal by automatically changing parameters used by the algorithm with little input from a user. The advan- tage of the modification is to reduce the guesswork needed …
-
Improving traffic management efficiency through reinforcement learning-based traffic signal control and citywide transit simulation
… and demonstrate that a novel approach using Neuroevolution outperforms Gradient Descent methods.
-
The evolution of coordinated cooperative behaviors
… of coordinated cooperation. An agent-based neuroevolutionary simulation of an ecosystem containing teams of predators and prey was built, modeling the environment of spotted hyenas. Communication, prey-capture rewards and reward-sharing strategies were found to determine whether cooperative …
-
Adversarial Learning through Red Teaming: From Data to Behaviour
… learning agent) and a natural red (human). Neuroevolution is selected as the computational model, owing to its abilities to evolve and learn which are very important to mimic human behaviours. Besides that, neural networks are used to approximate human behaviours from the data collected in …
-
Artificial Intelligence for a Castle Conquest Simulation Game
Umělá inteligence představuje široce zkoumaný obor, který významně přispívá k vý- voji nových technologií. Existuje mnoho různých přístupů k implementaci umělé inteli- gence a hry mohou sloužit jako prostředí užitečné pro jejich testování. Tato práce má za cíl vytvořit jednoduchou strategickou hru …
-
Neuronové sítě a genetické algoritmy
Tato práce se zabývá evolučními a genetickými algoritmy a jejich možnou spoluprací při tvorbě a učení neuronových sítí. V teoretické části jsou popsány genetické algoritmy a neuronové sítě. Také jsou popsány možnosti jejich kombinace a je proveden přehled existujících algoritmů. V praktické části …
-
Deep learning-based seagrass detection and classification from underwater digital images
… the development of CNNs. The proposed deep neuroevolutionary algorithm (OFDA-CNN) outperformed other eight popular optimisation-based neuroevolutionary algorithms on a newly developed multi-species seagrass dataset. The OFDA-CNN algorithm also outperformed the state-of-the-art multi-species …