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.
In situations where some risk of injury is unavoidable for self-driving vehicles, how risk is distributed becomes an ethical question. Geisslinger and colleagues have developed a planning algorithm that takes five ethical principles into account and aims to comply with the emerging EU regulatory recommendations.
Olfactory navigation is a well-studied topic in insect behaviour, but many aspects of the challenging task of odour plume tracking are unknown. In a deep reinforcement learning approach, artificial agents are trained to produce (in silico) trajectories to localize the source of an odour plume, showing dynamics that mimic real insect behaviours.
When it comes to reasoning about the motion of physical objects, humans have natural intuitive physics knowledge. To test how good artificial learning agents are in similar predictive abilities, Xue and colleagues present a benchmark based on a two-dimensional physics environment in which 15 physical reasoning skills are measured.
AI language modelling and generation approaches have developed fast in the last decade, opening promising new directions in human–AI collaboration. An AI-in-the loop conversational system called HAILEY is developed to empower peer supporters in providing empathic responses to mental health support seekers.
The reconstruction of spatially resolved information of an extended object from an observed intensity diffraction pattern in holographic imaging is a challenging problem. By incorporating an explicit physical model, Lee and colleagues propose a deep learning method that can be used in holographic image reconstruction under physical perturbations and which generalizes well beyond object-to-sensor distances and pixel sizes seen during training.
Despite recent improvements in microscopy acquisition methods, extracting quantitative information from biological experiments in crowded conditions is a challenging task. Pineda and colleagues propose a geometric deep-learning-based framework for automated trajectory linking and dynamical property estimation that is able to effectively deal with complex biological scenarios.
Large language models have recently emerged with extraordinary capabilities, and these methods can be applied to model other kinds of sequence, such as string representations of molecules. Ross and colleagues have created a transformer-based model, trained on a large dataset of molecules, which provides good results on property prediction tasks.
Liquid chromatography–tandem mass spectrometry (LC-MS2) provides high-throughput screening of molecules with a large number of features. But these features are difficult to associate with specific molecular structures of each sample. To improve structure prediction from these features, Bach et al. propose a machine learning model trained to also take into account stereochemistry to combine the different kinds of features provided by LC-MS2.
There is growing interest in using sophisticated machine learning models for the prediction of molecular properties, such as potency of novel drugs. However, Janela and Bajorath show that simple nearest-neighbour analysis meets or exceeds the accuracy of state-of-the-art complex machine learning methods and that randomized prediction models still reproduce compound potency values within an order of magnitude.
The design of legged robots with agility and speed is challenging. The authors present a method with reinforcement learning-based controllers for locomotion control of quadruped robots. The pipeline achieves improvements in performance, such as running speed.
Predicting RNA degradation is a fundamental task in designing RNA-based therapeutics. Two crowdsourcing platforms, Kaggle and Eterna, united to develop accurate deep learning models for RNA degradation on a timescale of 6 months.
The problem of reconstructing full-field quantities from incomplete observations arises in various real-world applications. Güemes and colleagues propose a super-resolution algorithm based on a generative adversarial network that can achieve reconstruction of the underlying field from random sparse measurements without requiring full-field high-resolution training data.
Evolutionary computation is a very active field of research, with an ever-growing number of metaheuristic optimization algorithms being published. A serious problem plaguing the field is the use of inadequate benchmarks. Kudela exposes the issue and provides recommendations that can help to fairly evaluate and compare new methods.
Learning minimal representations of dynamical systems is essential for mathematical modelling and prediction in science and engineering. Floryan and Graham propose a deep learning framework able to estimate accurate global dynamical models by sewing together multiple local representations learnt from high-dimensional time-series data.
Advances in ultra-widefield retinal imaging have created a need for automated disease detection. Engelmann and colleagues develop a deep learning model for the detection of retinal diseases. They evaluate it under more realistic conditions than has been considered previously and investigate what regions of ultra-widefield images are important for the performance of such a model.
In recent years, deep learning techniques have enhanced the possibility to extract useful, high-resolution physical information from electron and scanning probe microscopy images. AtomAI, an open-source software package, can accelerate this process by bringing deep learning and simulation tools into a single framework for a range of instruments.