AIMC Topic: Biological Evolution

Clear Filters Showing 1 to 10 of 159 articles

What does evolution make? Learning in living lineages and machines.

Trends in genetics : TIG
How does genomic information unfold, to give rise to self-constructing living organisms with problem-solving capacities at all levels of organization? We review recent progress that unifies work in developmental genetics and machine learning (ML) to ...

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 ...

Exploring the evolutionary adaptations of the unique seahorse tail's muscle architecture through modelling and robotic prototyping.

Journal of the Royal Society, Interface
Seahorses possess a unique tail muscle architecture that enables efficient grasping and anchoring onto objects. This prehensile ability is crucial for their survival, as it allows them to resist currents, cling to mates during reproduction and remain...

A neural network model for the evolution of reconstructive social learning.

Scientific reports
Learning from others is an important adaptation. However, the evolution of social learning and its role in the spread of socially transmitted information are not well understood. Few models of social learning account for the fact that socially transm...

Colonial bacterial memetic algorithm and its application on a darts playing robot.

Scientific reports
In this paper, we present the Colonial Bacterial Memetic Algorithm (CBMA), an advanced evolutionary optimization approach for robotic applications. CBMA extends the Bacterial Memetic Algorithm by integrating Cultural Algorithms and co-evolutionary dy...

Neuroevolution insights into biological neural computation.

Science (New York, N.Y.)
This article reviews existing work and future opportunities in neuroevolution, an area of machine learning in which evolutionary optimization methods such as genetic algorithms are used to construct neural networks to achieve desired behavior. The ar...

Psychophysiological foundations of human physical activity behavior and motivation: theories, systems, mechanisms, evolution, and genetics.

Physiological reviews
Physical activity is a meaningful part of life that starts before birth and lasts until death. There are many health benefits to be derived from physical activity; hence, regular engagement is recommended on a weekly basis. However, these recommendat...

Neural networks through the lens of evolutionary dynamics.

Bio Systems
This article revisits Artificial Neural Networks (NNs) through the lens of Evolutionary Dynamics. The two most important features of NNs are shown to reflect the two most general processes of Evolutionary Dynamics. This overlap may serve as a new and...

Adapting to time: Why nature may have evolved a diverse set of neurons.

PLoS computational biology
Brains have evolved diverse neurons with varying morphologies and dynamics that impact temporal information processing. In contrast, most neural network models use homogeneous units that vary only in spatial parameters (weights and biases). To explor...

Inferring the locomotor ecology of two of the oldest fossil squirrels: influence of operationalization, trait, body size and machine learning method.

Proceedings. Biological sciences
Correlations between morphology and lifestyle of extant taxa are useful for predicting lifestyles of extinct relatives. Here, we infer the locomotor behaviour of from the middle Oligocene and from the lower Miocene of France using their femoral mor...