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.
3D image reconstruction is important for the understanding of materials and their function in devices. A generative adversarial network architecture reconstructs 3D materials microstructures from 2D images.
At the heart of many challenges in scientific research lie complex equations for which no analytical solutions exist. A new neural network model called DeepONet can learn to approximate nonlinear functions as well as operators.
Neuromorphic computing could unlock low-power machine learning that can run on edge devices. A new algorithm that implements an artificial neuron emitting a sparse number of spikes could help realize this goal.
Computational models that capture the nonlinear processing of the inner ear have been prohibitively slow to use for most machine-hearing systems. A convolutional neural network model replicates hallmark features of cochlear signal processing, potentially enabling real-time applications.
Chemical reactions can be grouped into classes, but determining what class a specific reaction belongs to is not trivial on a large-scale. A new study demonstrates data-driven automatic classification of chemical reactions with methods borrowed from natural language processing.
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.
Photonic computing devices are a compelling alternative to conventional computing setups for machine learning applications, as they are nonlinear, fast and easy to parallelize. Recent work demonstrates the potential of these optical systems to process and classify human motion from video.
Origami engineering has long held the promise of complex and futuristic machines. A new foldable haptics system shows that this paradigm can be functional as well.
Loss-of-function mutations in metal-binding proteins are heavily implicated with numerous diseases, and identifying such ‘cracks’ will be valuable to biologists and medical doctors in the study and treatment of disease. A deep learning approach has been developed to tackle this challenging task.
In cooperative games, humans are biased against AI systems even when such systems behave better than our human counterparts. This raises a question: should AI systems ever be allowed to conceal their true nature and lie to us for our own benefit?
Adversarial attacks make imperceptible changes to a neural network’s inputs so that it recognizes it as something entirely different. This flaw can give us insight into how these networks work and how to make them more robust.