Essays about: "evolutionary algorithms"
Showing result 16 - 20 of 71 essays containing the words evolutionary algorithms.
-
16. Self-Optimization of Camera Hardware
University essay from Lunds universitet/Institutionen för datavetenskapAbstract : This thesis aims to investigate the automatic tuning of hardware parameters in a camera's image processing pipeline. In order to solve the tuning problem, it is formulated as a black-box optimization problem centered around a physical camera unit. Optimization is performed by comparing the camera's output to a reference image. READ MORE
-
17. A scalable species-based genetic algorithm for reinforcement learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Existing methods in Reinforcement Learning (RL) that rely on gradient estimates suffer from the slow rate of convergence, poor sample efficiency, and computationally expensive training, especially when dealing with complex real-world problems with a sizable dimensionality of the state and action space. In this work, we attempt to leverage the benefits of evolutionary computation as a competitive, scalable, and gradient-free alternative to training deep neural networks for RL-specific problems. READ MORE
-
18. MACHINE LEARNING-ASSISTED LOAD TESTING
University essay from Mälardalens högskola/Akademin för innovation, design och teknikAbstract : The increasing worldwide demand for software systems involved in society has led to the need where not only functionality is fundamental and addressed, but end-user satisfaction in terms of availability, throughput, and response time is essential and should be preserved. Thus, systems must be evaluated at preset load levels to assess the non-functional quality problems from the closest perspective of real application use. READ MORE
-
19. Hyperparameter Optimization for Convolutional Neural Networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Training algorithms for artificial neural networks depend on parameters called the hyperparameters. They can have a strong influence on the trained model but are often chosen manually with trial and error experiments. READ MORE
-
20. Learning stationary tasks using behavior trees and genetic algorithms
University essay from Uppsala universitet/Avdelningen för systemteknikAbstract : The demand for collaborative, easy to use robots has increased during the last decades in hope of incorporating the use of robotics in smaller production scales, with easier and faster programming. Artificial intelligence (AI) and Machine learning (ML) are showing promising potential in robotics and this project has attempted to automatically solve a specific assembly task with Behavior trees (BTs). READ MORE