Reviews & Analysis

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.

Deep learning has resulted in impressive achievements, but under what circumstances does it fail, and why? The authors propose that its failures are a consequence of shortcut learning, a common characteristic across biological and artificial systems in which strategies that appear to have solved a problem fail unexpectedly under different circumstances.

Autonomous driving technology is improving, although doubts about their reliability remain. Controllers based on compact neural architectures could help improve their interpretability and robustness.

Robots could play an important part in transforming healthcare to cope with the COVID-19 pandemic. This Perspective highlights how robotic technology integrated in a range of tasks in the surgical environment could help to ensure a continuation of medical services while reducing the risk of infection.

Drug discovery has recently profited greatly from the use of deep learning models. However, these models can be notoriously hard to interpret. In this Review, Jiménez-Luna and colleagues summarize recent approaches to use explainable artificial intelligence techniques in drug discovery.

Evidence syntheses produced from the scientific literature are important tools for policymakers. Producing such evidence syntheses can be highly time- and labour-consuming but machine learning models can help as already demonstrated in the health and medical sciences. This Perspective describes a machine learning-based framework specifically designed to support evidence syntheses in the area of agricultural research, for tackling the UN Sustainable Development Goal 2: zero hunger by 2030.

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.

Recent developments in machine learning have seen the merging of ensemble and deep learning techniques. The authors review advances in ensemble deep learning methods and their applications in bioinformatics, and discuss the challenges and opportunities going forward.

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.

Developing swarm robots for a specific application is a time consuming process and can be alleviated by automated optimization of the behaviour. Birattari and colleagues discuss that there are two fundamentally different design approaches; a semi-autonomous one, which allows for situation specific tuning from human engineers and one that needs to be entirely autonomous.

This review covers the history of procedural content generation (PCG) approaches for video games, and how these approaches are now used to generate training data and environments for machine learning models. The authors then discuss how PCG may be crucial for training agents which generalise well.

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.

Machine learning models are commonly used to predict risks and outcomes in biomedical research. But healthcare often requires information about cause–effect relations and alternative scenarios, that is, counterfactuals. Prosperi et al. discuss the importance of interventional and counterfactual models, as opposed to purely predictive models, in the context of precision medicine.

China’s New Generation Artificial Intelligence Development Plan was launched in 2017 and lays out an ambitious strategy, which intends to make China one of the world’s premier AI innovation centre by 2030. This Perspective presents the view from a group of Chinese AI experts from academia and industry about the origins of the plan, the motivations and main focus for attention from research and industry.

Medical imaging data is often subject to privacy and intellectual property restrictions. AI techniques can help out by offering tools like federated learning to bridge the gap between personal data protection and data utilisation for research and clinical routine, but these tools need to be secure.

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.

As artists are beginning to employ deep learning techniques to create new and interesting art, questions arise about how copyright and ownership apply to those works. This Perspective discusses how artists, programmers and users can ensure clarity about the ownership of their creations.

Predicting the properties of batteries, such as their state of charge and remaining lifetime, is crucial for improving battery manufacturing, usage and optimisation for energy storage. The authors discuss how machine learning methods and high-throughput experimentation provide a data-driven approach to this problem, and highlight challenges in building models which provide fast and accurate battery state predictions.