Deap

Rainville, François-Michel De; Fortin, F.; Gardner, Marc-André; Parizeau, Marc; Gagné, Christian

doi:10.1145/2330784.2330799

Cited by 133 publications

(34 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The deformation from the FEM simulation is used to evaluate the generated magnetization distribution through a fitness function (see Supporting Information for more details). Selection, crossover, and mutation steps of the EA are conducted by using an open‐source evolutionary computation framework to create new magnetization distributions until the desired deformation with a small enough fitness function value or the predetermined maximum number of generations is reached . The detailed algorithm information regarding the algorithm is shown in Supporting Information.…”

Section: Resultsmentioning

confidence: 99%

Evolutionary Algorithm‐Guided Voxel‐Encoding Printing of Functional Hard‐Magnetic Soft Active Materials

Hamel

et al. 2020

Advanced Intelligent Systems

113

View full text Add to dashboard Cite

Hard‐magnetic soft active materials (hmSAMs), embedding hard‐magnetic particles in soft polymeric matrices, have attracted a great number of research interests due to their fast‐transforming, untethered control, as well as excellent programmability. However, the current direct‐ink‐write (DIW) printing‐based fabrication of hmSAM parts and structures only permits programmable magnetic direction with a constant magnetic density. Also, the existing designs rely on the brute‐force approach to generate the assignment of magnetization direction distribution, which can only produce intuitional deformations. These two factors greatly limit the design space and the application potentials of hmSAMs. Herein, a “voxel‐encoding DIW printing” method to program both the magnetic density and direction distributions during hmSAM printing is introduced. The voxel‐encoding DIW printing is then integrated with an evolutionary algorithm (EA)‐based design strategy to achieve the desired magnetic actuation and motion with complex geometry variations and curvature distributions. With the new EA‐guided voxel‐encoding DIW printing technique, the functional hmSAMs that produce complicated shape morphing with desired curvature distributions for advanced applications such as biomimetic motions are demonstrated. These demonstrations indicate that the proposed EA‐guided voxel‐encoding DIW printing method significantly broadens the application potentials of hmSAMs.

show abstract

Section: Resultsmentioning

confidence: 99%

Evolutionary Algorithm‐Guided Voxel‐Encoding Printing of Functional Hard‐Magnetic Soft Active Materials

Hamel

et al. 2020

Advanced Intelligent Systems

113

View full text Add to dashboard Cite

show abstract

“…1 . The Non-dominated Sorted Genetic Algorithm ( nsga-ii ) [ 79 ] from the Distributed Evolutionary Algorithms in Python ( deap ) [ 80 ] package was used in combination with the COBRApy package [ 78 ] for FBA evaluation. Equal weight was placed on reducing the number of reactions used in the model, whilst maximizing the biomass output.…”

Section: Methodsmentioning

confidence: 99%

Simulating the evolutionary trajectories of metabolic pathways for insect symbionts in the genus Sodalis

et al. 2020

View full text Add to dashboard Cite

Insect–bacterial symbioses are ubiquitous, but there is still much to uncover about how these relationships establish, persist and evolve. The tsetse endosymbiont Sodalis glossinidius displays intriguing metabolic adaptations to its microenvironment, but the process by which this relationship evolved remains to be elucidated. The recent chance discovery of the free-living species of the genus Sodalis , Sodalis praecaptivus , provides a serendipitous starting point from which to investigate the evolution of this symbiosis. Here, we present a flux balance model for S. praecaptivus and empirically verify its predictions. Metabolic modelling is used in combination with a multi-objective evolutionary algorithm to explore the trajectories that S. glossinidius may have undertaken from this starting point after becoming internalized. The order in which key genes are lost is shown to influence the evolved populations, providing possible targets for future in vitro genetic manipulation. This method provides a detailed perspective on possible evolutionary trajectories for S. glossinidius in this fundamental process of evolutionary and ecological change.

show abstract

“…The search over candidate model structures and parameterizations employs a customized genetic programming algorithm, an evolutionary approach that encodes mathematical expressions in a tree structure to support symbolic regression. Modular components of the algorithm were drawn from the package Distributed Evolutionary Algorithms in Python, or DEAP (De Rainville et al, 2012). As depicted in the Model Generation panel of Figure 2, mutation and crossover operators act on ordered representations of models, where each tree is flattened into an ordered list of elements, to generate new structures from promising candidates and explore the model space during optimization.…”

Section: Search Algorithmmentioning

confidence: 99%

Toward Data‐Driven Generation and Evaluation of Model Structure for Integrated Representations of Human Behavior in Water Resources Systems

Ekblad

Herman

2021

Water Resources Research

View full text Add to dashboard Cite

Simulations of human behavior in water resources systems are challenged by uncertainty in model structure and parameters. The increasing availability of observations describing these systems provides the opportunity to infer a set of plausible model structures using data‐driven approaches. This study develops a three‐phase approach to the inference of model structures and parameterizations from data: problem definition, model generation, and model evaluation, illustrated on a case study of land use decisions in the Tulare Basin, California. We encode the generalized decision problem as an arbitrary mapping from a high‐dimensional data space to the action of interest and use multiobjective genetic programming to search over a family of functions that perform this mapping for both regression and classification tasks. To facilitate the discovery of models that are both realistic and interpretable, the algorithm selects model structures based on multiobjective optimization of (1) their performance on a training set and (2) complexity, measured by the number of variables, constants, and operations composing the model. After training, optimal model structures are further evaluated according to their ability to generalize to held‐out test data and clustered based on their performance, complexity, and generalization properties. Finally, we diagnose the causes of good and bad generalization by performing sensitivity analysis across model inputs and within model clusters. This study serves as a template to inform and automate the problem‐dependent task of constructing robust data‐driven model structures to describe human behavior in water resources systems.

show abstract

Deap

Cited by 133 publications

References 9 publications

Evolutionary Algorithm‐Guided Voxel‐Encoding Printing of Functional Hard‐Magnetic Soft Active Materials

Evolutionary Algorithm‐Guided Voxel‐Encoding Printing of Functional Hard‐Magnetic Soft Active Materials

Simulating the evolutionary trajectories of metabolic pathways for insect symbionts in the genus Sodalis

Toward Data‐Driven Generation and Evaluation of Model Structure for Integrated Representations of Human Behavior in Water Resources Systems

Contact Info

Product

Resources

About