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.
Microrobots can interact intelligently with their environment and complete specific tasks by well-designed incorporation of responsive materials. Recent work demonstrates how swarms of microbots with specifically tuned surface chemistry can remove a hormone pollutant from a solution by coalescing it into a web.
Autonomous driving technology is improving, although doubts about their reliability remain. Controllers based on compact neural architectures could help improve their interpretability and robustness.
Finding states of matter with properties that are just right is a main challenge from metallurgy to quantum computing. A data-driven optimization approach based on gaming strategies could help.
The proper response to an ever-changing environment depends on the ability to quantify elapsed time, memorize short intervals and forecast when an upcoming experience may occur. A recent study describes the encoding principles of these three types of time using computational modelling.
Bayesian networks can capture causal relations, but learning such a network from data is NP-hard. Recent work has made it possible to approximate this problem as a continuous optimization task that can be solved efficiently with well-established numerical techniques.
An important task in system biology is to understand cellular processes through the lens of gene sets and their expression patterns. Machine learning can help, but genes form complex interaction networks, and levarging this information in machine learning applications requires a sophisticated data representation.
To deploy robot swarms in our daily lives, they need to be resilient to malfunctioning errors and protected against malicious attacks. Blockchain technology could provide an essential level of protection.
Recurrent networks can be trained using a generalization of backpropagation, called backpropagation through time, but a gap exists between the mathematics of this learning algorithm and biological plausibility. E-prop is a biologically inspired alternative that opens up possibilities for a new generation of online training algorithms for recurrent networks.
Our understanding of concepts can differ depending on the modality — such as vision, text or speech — through which we learn this concept. A recent study uses computational modelling to demonstrate how conceptual understanding aligns across modalities.
Tree-based models are among the most popular and successful machine learning algorithms in practice. New tools allow us to explain the predictions and gain insight into the global behaviour of these models.