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 17 of 17 for “"evolution strategy"”.
-
Comparison of Strategies for the Constraint Determination of Simulink Models
… supported by NASA whose focus was to develop a strategy to constrain the outputs of a Simulink model. Simulink models are quite similar to mathematical functions and therefore optimization algorithms can be applied to constrain the outputs. Optimizations of simple mathematical functions paved …
-
Comparison of Strategies for the Constraint Determination of Simulink Models
… supported by NASA whose focus was to develop a strategy to constrain the outputs of a Simulink model. Simulink models are quite similar to mathematical functions and therefore optimization algorithms can be applied to constrain the outputs. Optimizations of simple mathematical functions paved …
-
Selecting appropriate reinforcement-learning algorithms for robot manipulation domains
… algorithms: Covariance Matrix Adaptation Evolution Strategy, Deep Deterministic Policy Gradients, and Proximal Policy Optimization. We compare their performance on various target domains to measure quantitatively their dependence on varied features of the environment. We study the effect …
-
Multi-objective evolutionary algorithms for product design
… Chemistry and Machine Learning (ML) with Evolutionary MultiObjective Optimisation (EMOO) techniques to streamline compound design. This approach automates the design process by leveraging ML to accurately predict compound properties and using EMOO to select compounds that meet various …
-
Mixed-precision NN accelerator with neural-hardware architecture search
… of a neural network accelerator. It includes the evolution strategy based hardware architecture search and one-shot HyperNet based quantized neural architecture search. Evaluated on existing DNN benchmarks, our mixed-precision accelerator achieves 11.7x, 1.5x speedup and 10.5x, 1.9x energy savings …
-
Towards The Development Of Intrinsically Fluorescent Unnatural Amino Acids For In Vivo Incorporation Into Proteins
… Acd to the growing protein chain. This labeling strategy has aided several previous biophysical studies involving fluorescence polarization (FP) and Förster resonance energy transfer (FRET) measurements, but to date was limited to solely E. coli expressed proteins. This thesis work will continue …
-
Exploring embedding vectors for emotion detection
… using the covariance matrix adap- tation evolution strategy (CMA-ES). Our method produces state of the art results, surpassing classic supervised learning methods.
-
Measurement of ignition delay time of jet fuels in shock tube for the development of the chemical kinetic mechanism
… CycloSAF. A Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is then employed to optimize selected Arrhenius parameters of the 16 lumped HyChem reactions using a multi-objective function that combines ignition-delay RMSE and L1/L2-type regularization, with tight parameter bounds to …
-
Design problem optimization with multi-objective evolutionary algorithms
… and comparing two advanced multi-objective evolutionary algorithms—Multi-Objective Covariance Matrix Adaptation Evolution Strategy (MOCMA-ES) and the Non-Dominated Sorting Genetic Algorithm II (NSGA-II)—to optimize sunshades across five key objectives: thermal comfort, energy consumption, …
-
Power System Dynamic Control and Performance Improvement Based on Reinforcement Learning
… called Guided Surrogate Gradient-based Evolution Strategy (GSES) determines the weights of the policy (which generates the action for our control reference signal) without back-propagation process for gradient update using a simultaneous perturbation stochastic approximation approach …
-
Patient-specific technology for in vivo assessment of 3-D spinal motion
… stochastic approach, covariance matrix adaptive evolution strategy, was used as the optimizing function. The newly developed interpolation algorithm was used to reduce the sample size of the bi-planar fluoroscopic images which reduces radiation exposure. Experimental results illustrate the …
-
New strategies for in vivo continuous directed evolution
Continuous in vivo directed evolution facilitates the exploration of large biomolecule libraries at unprecedented speeds. By inserting a biomolecule of interest into a constantly mutating virus whose replicative capacity has been rendered dependent on the desired activity of that biomolecule, the …
-
2D-3D Registration Methods for Computer-Assisted Orthopaedic Surgery
… Filter (UKF) and Covariance Matrix Adaptation Evolution Strategy (CMA-ES), to improve the capture range for the 2D-3D registration problem; 2) a multiple-object 2D-3D registration technique is proposed that simultaneously aligns multiple 3D images of fracture fragments to a set of fluoroscopic …
-
Dynamic identification of the Augusta hybrid base isolated building using data from full scale push and sudden release tests
… domain using the Covariance Matrix Adaptation Evolution Strategy, a stochastic algorithm for difficult, non linear black-box optimization. The identification of the isolation system provided the mass of the rigid block, the bi-linear properties used in the mechanical representation of the …
-
Evolutionary Algorithm For Large-Scale Optimization
… function. To deal with these issues, several Evolutionary Algorithms (EAs) based on the divide-and-conquer concept have been proposed. A popular approach in this area is Cooperative Co-evolution (CC) which usually divides a problem into a number of smaller sub-problems that can be optimized …
-
Genome engineering in saccharomyces cerevisiae
… of complex biological systems. Directed evolution, on the other hand, has been proved as a better strategy by performing iterative cycles of mutagenesis and selection. Current practice of directed evolution is mostly confined to individual proteins, due to the lack of efficient tools to …
-
Xenobiology in synthetic biology: From non-standard amino acid incorporation to biosecurity implications
… incorporation of the nsAA, are needed. Current evolution methods for aaRS are limited in library design and alternative continuous evolution systems are not straightforward and can be hard to evaluate. To address this first bottleneck, we established and validated a Nanopore sequencing guided …