AIMC Topic: Biological Evolution

Clear Filters Showing 131 to 140 of 169 articles

Unsupervised feature selection with evolutionary sparsity.

Neural networks : the official journal of the International Neural Network Society
The ℓ-norm is playing an increasingly important role in unsupervised feature selection. However, existing algorithm for optimization problem with ℓ-norm constraint has two problems: First, they cannot automatically determine the sparsity, also known ...

Premolar Ecomorphology in Anthropoid Primates: A Machine Learning Approach.

Journal of morphology
Reconstructing the diets of extinct taxa is essential for understanding their ecologies and evolutionary histories, yet traditional methods and proxies such as molar morphology have limited resolution. The potential of premolar morphology as a dietar...

Ultraviolet in swallowtail butterflies: contrasted dorso-ventral evolution highlights a trade-off between natural and sexual selection on visual cues.

Evolution; international journal of organic evolution
The evolutionary dynamics of color pattern diversification in animals is strongly influenced by visual interactions within and among species. While much attention has been given to color pattern variation in the human-visible range, perception outsid...

Evolution of gene regulatory networks in insects.

Current opinion in insect science
Changes in gene regulatory networks (GRNs) underlying the evolution of traits have been intensively studied, with insects providing excellent model cases. In studies using Drosophila, butterflies, and other insects, several well-known cases have show...

Evolutionary multi-agent reinforcement learning in group social dilemmas.

Chaos (Woodbury, N.Y.)
Reinforcement learning (RL) is a powerful machine learning technique that has been successfully applied to a wide variety of problems. However, it can be unpredictable and produce suboptimal results in complicated learning environments. This is espec...

The Role of Morphological Variation in Evolutionary Robotics: Maximizing Performance and Robustness.

Evolutionary computation
Exposing an evolutionary algorithm that is used to evolve robot controllers to variable conditions is necessary to obtain solutions which are robust and can cross the reality gap. However, we do not yet have methods for analyzing and understanding th...

Neural Architecture Search Using Covariance Matrix Adaptation Evolution Strategy.

Evolutionary computation
Evolution-based neural architecture search methods have shown promising results, but they require high computational resources because these methods involve training each candidate architecture from scratch and then evaluating its fitness, which resu...

Enhancing cryo-EM structure prediction with DeepTracer and AlphaFold2 integration.

Briefings in bioinformatics
Understanding the protein structures is invaluable in various biomedical applications, such as vaccine development. Protein structure model building from experimental electron density maps is a time-consuming and labor-intensive task. To address the ...

Inferring Historical Introgression with Deep Learning.

Systematic biology
Resolving phylogenetic relationships among taxa remains a challenge in the era of big data due to the presence of genetic admixture in a wide range of organisms. Rapidly developing sequencing technologies and statistical tests enable evolutionary rel...

Evolving Modularity in Soft Robots Through an Embodied and Self-Organizing Neural Controller.

Artificial life
Modularity is a desirable property for embodied agents, as it could foster their suitability to different domains by disassembling them into transferable modules that can be reassembled differently. We focus on a class of embodied agents known as vox...