Sökning: "evolutionary computation"
Visar resultat 1 - 5 av 11 uppsatser innehållade orden evolutionary computation.
1. EMONAS : Evolutionary Multi-objective Neuron Architecture Search of Deep Neural Network
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Customized Deep Neural Network (DNN) accelerators have been increasingly popular in various applications, from autonomous driving and natural language processing to healthcare and finance, etc. However, deploying them directly on embedded system peripherals within real-time operating systems (RTOS) is not easy due to the paradox of the complexity of DNNs and the simplicity of embedded system devices. LÄS MER
2. Capacitated Multi Depot Green Vehicle Routing for Transporting End-of-Life electrical waste : A practical study on environmental and social sustainability within the field of CMDGVRP with heterogeneous fleets
Uppsats för yrkesexamina på avancerad nivå, Högskolan i Halmstad/Akademin för informationsteknologiSammanfattning : A comprehensive study is presented of the Capacitated Multi DepotGreen Vehicle Routing Problem (CMDGVRP) applied to a heterogeneous fleet of electronic waste collecting vehicles with two objectives: to reduce the total fuel consumption of the vehicles (environmental sustainability) and to limit the continuous drive-time of the drivers (social sustainability). Research has been limited from this aspect, and in this study, the focus is on the practical application of pickup and delivery of electronic waste. LÄS MER
3. Symbolic Regression using Genetic Programming Leveraging Neural Information Processing
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Regression analysis conducted with traditional mathematical methods can be sub-optimal if the exact model of the observed data is unknown. Evolutionary computing (EC) and deep learning (DL) are viable alternatives, since regression performed with these methods tends to be less dependent on a particular model. LÄS MER
4. A scalable species-based genetic algorithm for reinforcement learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : 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. LÄS MER
5. Convergence Properties for Different Null Space Bases When Solving the Initial Margin Optimization Problem Using CMA-ES
Master-uppsats, KTH/Matematisk statistikSammanfattning : This thesis evaluates how the evolutionary algorithm CMA-ES (Covariance Matrix Adaption Evolution Strategy) can be used for optimizing the total initial margin for a network of banks trading bilateral OTC derivatives. The algorithm is a stochastic method for optimization of non-linear and, but not limited to, non-convex functions. LÄS MER
