Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Could this be the year that AI is going to surpass human performance in playing the popular video game Angry Birds? The organizers of the annual AIBIRDS competition discuss the challenges involved.
Civil liberty groups are raising the alarm over the ubiquitous use of automated facial recognition. As a society, we need to decide on the acceptable use of this technology and how to build in safeguards to protect human rights.
Neural networks are a promising digital pathology tool but are often criticized for their limited explainability. Faust and others demonstrate how machine-learned features correlate with human-understandable histological patterns and groupings, permitting increased transparency of deep learning tools in medicine.
Classical statistical analysis in many empirical sciences has lagged behind modern trends in analytics for large-scale datasets. The authors discuss the influence of more variables, larger sample sizes, open data sources for analysis and assessment, and ‘black box’ prediction methods on the empirical sciences, and provide examples from imaging neuroscience.
Artists have always been at the forefront of experimenting with digital tools. The AI: More than Human exhibition at the Barbican Centre, London (until August 26th), features some intriguing AI-inspired installations. We spoke to four artists about their work and influences.
Artificial intelligence approaches can aid medicinal chemists to creatively look for new chemical entities with drug-like properties. A rule-based approach combined with a machine learning model was trained on successful synthetic routes described in chemical patent literature. This process produced computer-generated compounds that mimic known medicines.
Rebuilding particle trajectories from high-energy proton collisions is an essential step in processing the petabytes of data generated by the Large Hadron Collider at CERN. In search of an order of magnitude speed-up, physicists reached out to the computer science community.
Reducing the radiation dose for medical CT scans can provide a less invasive imaging method, but requires a method for reconstructing an image up to the image quality from a full-dose scan. In this article, Wang and colleagues show that the deep learning approach, combined with the feedback from radiologists, produces higher quality reconstructions than or similar to that using the current commercial methods.
High-throughput brain image registration methods that are independent of any pre-processing steps, and are robust under mild image transformations, could accelerate the study of region-specific changes in brain development. A deep learning-based method is therefore developed for automated registration through segmenting brain regions of interest with minimal human supervision.
To develop scientific methods for evaluation in robotics, the field requires a more stringent definition of the subject of study, says Signe Redfield, focusing on capabilities instead of physical systems.
Effy Vayena runs a lab at ETH Zürich that studies ethics, legal and social implications of precision medicine and digital health. We asked her views on the code of conduct for using artificial intelligence (AI) systems in healthcare, recently published by the UK’s National Health Service (NHS).
Deep learning has revolutionized the technology industry, but beyond eye-catching applications such as virtual assistants, recommender systems and self-driving cars, deep learning is also transforming many scientific fields.
Deep neural networks are a powerful tool for predicting protein function, but identifying the specific parts of a protein sequence that are relevant to its functions remains a challenge. An occlusion-based sensitivity technique helps interpret these deep neural networks, and can guide protein engineering by locating functionally relevant protein positions.