Related papers: Digging Deeper: Methodologies for High-Content Phe…
As is true of many complex tasks, the work of discovering, describing, and understanding the diversity of life on Earth (viz., biological systematics and taxonomy) requires many tools. Some of this work can be accomplished as it has been…
High-throughput phenotyping refers to the non-destructive and efficient evaluation of plant phenotypes. In recent years, it has been coupled with machine learning in order to improve the process of phenotyping plants by increasing…
Complex systems' modeling and simulation are powerful ways to investigate a multitude of natural phenomena providing extended knowledge on their structure and behavior. However, enhanced modeling and simulation require integration of…
One of the biggest challenges in biology is to understand how activity at the cellular level of neurons, as a result of their mutual interactions, leads to the observed behavior of an organism responding to a variety of environmental…
Accurate taxonomic identification of diatoms is essential for aquatic ecosystem monitoring, yet conventional methods depend heavily on expert taxonomists. Recent deep learning approaches improve automation, but most treat diatom recognition…
Tracking the abundance of underwater species is crucial for understanding the effects of climate change on marine ecosystems. Biologists typically monitor underwater sites with echosounders and visualize data as 2D images (echograms); they…
Understanding how information about external stimuli is transformed into behavior is one of the central goals of neuroscience. Here we characterize the information flow through a complete sensorimotor circuit: from stimulus, to sensory…
The techniques of deep learning have become the state of the art methodology for executing complicated tasks from various domains of computer vision, natural language processing, and several other areas. Due to its rapid development and…
Fluorescence microscopy allows for a detailed inspection of cells, cellular networks, and anatomical landmarks by staining with a variety of carefully-selected markers visualized as color channels. Quantitative characterization of…
Machine learning and deep learning have been celebrating many successes in the application to biological problems, especially in the domain of protein folding. Another equally complex and important question has received relatively little…
Gene innovation is a key mechanism on the evolution and phenotypic diversity of life forms. There is a need for tools able to study gene innovation across an increasingly large number of genomic sequences to maximally capitalise our…
Many microorganisms live and evolve in complex fluids. Examples include mammalian spermatozoa in cervical mucus, worms (e.g., \textit{C. elegans}) in wet soil, and bacteria (e.g., \textit{H. pylori}) in our stomach lining. Due to the…
Understanding the dynamics of genome rearrangements is a major issue of phylogenetics. Phylogenetics is the study of species evolution. A major goal of the field is to establish evolutionary relationships within groups of species, in order…
Recent efforts in neuroscience research seek to obtain detailed anatomical neuronal wiring maps as well as information on how neurons in these networks engage in dynamic activities. Although the entire connectivity map of the nervous system…
To survive in ever-changing environments, living organisms need to continuously combine the ongoing external inputs they receive, representing present conditions, with their dynamical internal state, which includes influences of past…
Mapping genotypes to phenotypes (G2P) is a fundamental goal in biology. So called PhyloG2P methods are a relatively new set of tools that leverage replicated evolution in phylogenetically independent lineages to identify genomic regions…
Camera traps are a proven tool in biology and specifically biodiversity research. However, camera traps including depth estimation are not widely deployed, despite providing valuable context about the scene and facilitating the automation…
We exploit flow propagation on the directed neuronal network of the nematode Caenorhabditis elegans to reveal dynamically relevant features of its connectome. We find flow-based groupings of neurons at different levels of granularity, which…
Today, deep learning represents the most popular and successful form of machine learning. Deep learning has revolutionised the field of pattern recognition, including biometric recognition. Biometric systems utilising deep learning have…
This work investigates the generalization behavior of deep neural networks (DNNs), focusing on the phenomenon of "fooling examples," where DNNs confidently classify inputs that appear random or unstructured to humans. To explore this…