Volume 5 Issue 6, June 2023

We show that large language models (LLMs), such as ChatGPT, can guide the robot design process, on both the conceptual and technical level, and we propose new human–AI co-design strategies and their societal implications.

There are repeated calls in the AI community to prioritize data work — collecting, curating, analysing and otherwise considering the quality of data. But this is not practised as much as advocates would like, often because of a lack of institutional and cultural incentives. One way to encourage data work would be to reframe it as more technically rigorous, and thereby integrate it into more-valued lines of research such as model innovation.

An in vitro biological system of cultured brain cells has learned to play Pong. This feat opens up an avenue towards the convergence of biological and machine intelligence.

A ‘programming’-like approach provides a one-step algorithm to find network parameters for recurrent neural networks that can model complex dynamical systems.

Although computer vision techniques are often data-driven, they can be enhanced by including the physical models underlying image formation as constraints. Achuta Kadambi et al. provide an overview of various techniques to incorporate physics into data-driven vision pipelines.

To fulfil the potential of quantum machine learning for practical applications in the near future, it needs to be robust against adversarial attacks. West and colleagues give an overview of recent developments in quantum adversarial machine learning, and outline key challenges and future research directions to advance the field.

There are numerous algorithms for generating Shapley value explanations. The authors provide a comprehensive survey of Shapley value feature attribution algorithms by disentangling and clarifying the fundamental challenges underlying their computation.

Worldwide weather station forecasting is challenging because of high computational costs and the difficulty of modelling spatiotemporal correlations from partial observations. Wu et al. propose a transformer-based method that can reconstruct such complex correlations from scattered weather stations, leading to efficient and interpretable state-of-the-art forecasts.

Designing methods to induce explicit and deep structural constraints in latent space at the sample level is an open problem in natural language processing-derived methods relying on transfer learning. McDermott and colleagues propose and analyse a pre-training framework imposing such structural constraints, and empirically demonstrate its advantages by showing that it outperforms existing pre-training state-of-the-art methods.

Recurrent neural networks are flexible architectures that can perform a variety of complex, time-dependent computations. Kim and Bassett introduce an alternative, ‘programming’-like computational framework to determine the appropriate network parameters for a specific task without the need for supervised training.

While single-cell multimodal datasets allow for the measurement of individual cells to understand cellular and molecular mechanisms, generating multimodal data for many cells is costly and challenging. Cohen Kalafut and colleagues develop a machine learning model capable of imputing single-cell modalities and prioritizing multimodal features, such as gene expression, chromatin accessibility and electrophysiology.

Immersive virtual reality requires artificial sensory perceptions to simulate what we feel and how we interact in the natural environment. Zhang and colleagues present a first-person, human-triggered, active haptic device that allows users to experience mechanical touching with various stiffness perceptions from positive to negative ranges, achieved by the unique benefits of curved origami.

Mass spectrometry imaging (MSI) can provide important information, but long imaging times are needed to achieve a high spatial resolution, which is why the amount of publicly available high-resolution MSI data for deep learning applications is limited. Liao and colleagues use transfer learning from optical super-resolution images to reduce the amount of MSI data that is needed.

Robots that can change their shape offer flexible functionality. A modular robotic platform is shown that implements physical polygon meshing, by combining triangles with sides of adjustable lengths, allowing flexible three-dimensional shape configurations.