The Experts below are selected from a list of 72624 Experts worldwide ranked by ideXlab platform
Theunis Piersma - One of the best experts on this subject based on the ideXlab platform.
-
Evolutionary Design of a flexible seasonally migratory avian phenotype why trade gizzard mass against pectoral muscle mass
2019Co-Authors: Anne Dekinga, Theunis Piersma, Kimberley J Mathot, Joseph B Burant, Petra Manche, Darren SaintongeAbstract:Migratory birds undergo impressive body remodelling over the course of an annual cycle. Prior to long-distance flights, red knots ( Calidris canutus islandica) reduce gizzard mass while increasing body mass and pectoral muscle mass. Although body mass and pectoral muscle mass are functionally linked via their joint effects on flight performance, gizzard and pectoral muscle mass are thought to be independently regulated. Current hypotheses for observed negative within-individual covariation between gizzard and pectoral muscle mass in free-living knots are based on a common factor (e.g. migration) simultaneously affecting both traits, and/or protein limitation forcing allocation decisions. We used diet manipulations to generate within-individual variation in gizzard mass and test for independence between gizzard and pectoral muscle mass within individuals outside the period of migration and under conditions of high protein availability. Contrary to our prediction, we observed a negative within-individual covariation between gizzard and pectoral muscle mass. We discuss this result as a potential outcome of an evolved mechanism underlying body remodelling associated with migration. Although our proposed mechanism requires empirical testing, this study echoes earlier calls for greater integration of studies of function and mechanism, and in particular, the need for more explicit consideration of the evolution of mechanisms underlying phenotypic Design.
Kimberley J Mathot - One of the best experts on this subject based on the ideXlab platform.
-
Evolutionary Design of a flexible seasonally migratory avian phenotype why trade gizzard mass against pectoral muscle mass
2019Co-Authors: Anne Dekinga, Theunis Piersma, Kimberley J Mathot, Joseph B Burant, Petra Manche, Darren SaintongeAbstract:Migratory birds undergo impressive body remodelling over the course of an annual cycle. Prior to long-distance flights, red knots ( Calidris canutus islandica) reduce gizzard mass while increasing body mass and pectoral muscle mass. Although body mass and pectoral muscle mass are functionally linked via their joint effects on flight performance, gizzard and pectoral muscle mass are thought to be independently regulated. Current hypotheses for observed negative within-individual covariation between gizzard and pectoral muscle mass in free-living knots are based on a common factor (e.g. migration) simultaneously affecting both traits, and/or protein limitation forcing allocation decisions. We used diet manipulations to generate within-individual variation in gizzard mass and test for independence between gizzard and pectoral muscle mass within individuals outside the period of migration and under conditions of high protein availability. Contrary to our prediction, we observed a negative within-individual covariation between gizzard and pectoral muscle mass. We discuss this result as a potential outcome of an evolved mechanism underlying body remodelling associated with migration. Although our proposed mechanism requires empirical testing, this study echoes earlier calls for greater integration of studies of function and mechanism, and in particular, the need for more explicit consideration of the evolution of mechanisms underlying phenotypic Design.
Wolfgang Banzhaf - One of the best experts on this subject based on the ideXlab platform.
-
multiobjective Evolutionary Design of deep convolutional neural networks for image classification
2021Co-Authors: Ian Whalen, Wolfgang Banzhaf, Yashesh D Dhebar, Kalyanmoy Deb, Erik D Goodman, Vishnu Naresh BoddetiAbstract:Convolutional neural networks (CNNs) are the backbones of deep learning paradigms for numerous vision tasks. Early advancements in CNN architectures are primarily driven by human expertise and by elaborate Design processes. Recently, neural architecture search was proposed with the aim of automating the network Design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: 1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario and 2) the search process requires vast computational resources in most approaches. To overcome these limitations, we propose an Evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating point operations (FLOPs). The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves computational efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning. The integration of these two main contributions allows an efficient Design of architectures that are competitive and in most cases outperform both manually and automatically Designed architectures on benchmark image classification datasets: CIFAR, ImageNet, and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature.
-
multi criterion Evolutionary Design of deep convolutional neural networks
2019Co-Authors: Ian Whalen, Wolfgang Banzhaf, Yashesh D Dhebar, Kalyanmoy Deb, Erik D Goodman, Vishnu Naresh BoddetiAbstract:Convolutional neural networks (CNNs) are the backbones of deep learning paradigms for numerous vision tasks. Early advancements in CNN architectures are primarily driven by human expertise and elaborate Design. Recently, neural architecture search was proposed with the aim of automating the network Design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited under limited computational budget for two reasons: (1) the obtained architectures are either solely optimized for classification performance or only for one targeted resource requirement; (2) the search process requires vast computational resources in most approaches. To overcome this limitation, we propose an Evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and FLOPs. The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves the computation efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among the past successful architectures through Bayesian Learning. The integration of these two main contributions allows an efficient Design of architectures that are competitive and in many cases outperform both manually and automatically Designed architectures on benchmark image classification datasets, CIFAR, ImageNet and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature.
-
multi objective Evolutionary Design of deep convolutional neural networks for image classification
2019Co-Authors: Ian Whalen, Wolfgang Banzhaf, Yashesh D Dhebar, Kalyanmoy Deb, Erik D Goodman, Vishnu Naresh BoddetiAbstract:Early advancements in convolutional neural networks (CNNs) architectures are primarily driven by human expertise and by elaborate Design processes. Recently, neural architecture search was proposed with the aim of automating the network Design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: (1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario; (2) the search process requires vast computational resources in most approaches. To overcome these limitations, we propose an Evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating-point operations (FLOPs). The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves computational efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning. The integration of these two main contributions allows an efficient Design of architectures that are competitive and in most cases outperform both manually and automatically Designed architectures on benchmark image classification datasets: CIFAR, ImageNet, and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature. Code is available at this https URL
-
on Evolutionary Design embodiment and artificial regulatory networks
2004Co-Authors: Wolfgang BanzhafAbstract:In this contribution we consider the idea that successful Evolutionary Design is best achieved in a networked system. We exemplify this thought by a discussion of artificial regulatory networks, a recently devised method to model natural genome-protein interactions. It is argued that emergent phenomena in nature require the existence of networks in order to become permanent.
Petra Manche - One of the best experts on this subject based on the ideXlab platform.
-
Evolutionary Design of a flexible seasonally migratory avian phenotype why trade gizzard mass against pectoral muscle mass
2019Co-Authors: Anne Dekinga, Theunis Piersma, Kimberley J Mathot, Joseph B Burant, Petra Manche, Darren SaintongeAbstract:Migratory birds undergo impressive body remodelling over the course of an annual cycle. Prior to long-distance flights, red knots ( Calidris canutus islandica) reduce gizzard mass while increasing body mass and pectoral muscle mass. Although body mass and pectoral muscle mass are functionally linked via their joint effects on flight performance, gizzard and pectoral muscle mass are thought to be independently regulated. Current hypotheses for observed negative within-individual covariation between gizzard and pectoral muscle mass in free-living knots are based on a common factor (e.g. migration) simultaneously affecting both traits, and/or protein limitation forcing allocation decisions. We used diet manipulations to generate within-individual variation in gizzard mass and test for independence between gizzard and pectoral muscle mass within individuals outside the period of migration and under conditions of high protein availability. Contrary to our prediction, we observed a negative within-individual covariation between gizzard and pectoral muscle mass. We discuss this result as a potential outcome of an evolved mechanism underlying body remodelling associated with migration. Although our proposed mechanism requires empirical testing, this study echoes earlier calls for greater integration of studies of function and mechanism, and in particular, the need for more explicit consideration of the evolution of mechanisms underlying phenotypic Design.
Joseph B Burant - One of the best experts on this subject based on the ideXlab platform.
-
Evolutionary Design of a flexible seasonally migratory avian phenotype why trade gizzard mass against pectoral muscle mass
2019Co-Authors: Anne Dekinga, Theunis Piersma, Kimberley J Mathot, Joseph B Burant, Petra Manche, Darren SaintongeAbstract:Migratory birds undergo impressive body remodelling over the course of an annual cycle. Prior to long-distance flights, red knots ( Calidris canutus islandica) reduce gizzard mass while increasing body mass and pectoral muscle mass. Although body mass and pectoral muscle mass are functionally linked via their joint effects on flight performance, gizzard and pectoral muscle mass are thought to be independently regulated. Current hypotheses for observed negative within-individual covariation between gizzard and pectoral muscle mass in free-living knots are based on a common factor (e.g. migration) simultaneously affecting both traits, and/or protein limitation forcing allocation decisions. We used diet manipulations to generate within-individual variation in gizzard mass and test for independence between gizzard and pectoral muscle mass within individuals outside the period of migration and under conditions of high protein availability. Contrary to our prediction, we observed a negative within-individual covariation between gizzard and pectoral muscle mass. We discuss this result as a potential outcome of an evolved mechanism underlying body remodelling associated with migration. Although our proposed mechanism requires empirical testing, this study echoes earlier calls for greater integration of studies of function and mechanism, and in particular, the need for more explicit consideration of the evolution of mechanisms underlying phenotypic Design.
