Reviews & Analysis

Tailoring the alignment of large language models (LLMs) to individuals is a new frontier in generative AI, but unbounded personalization can bring potential harm, such as large-scale profiling, privacy infringement and bias reinforcement. Kirk et al. develop a taxonomy for risks and benefits of personalized LLMs and discuss the need for normative decisions on what are acceptable bounds of personalization.

A classic question in cognitive science is whether learning requires innate, domain-specific inductive biases to solve visual tasks. A recent study trained machine-learning systems on the first-person visual experiences of children to show that visual knowledge can be learned in the absence of innate inductive biases about objects or space.

An emerging research area in AI is developing multi-agent capabilities with collections of interacting AI systems. Andrea Soltoggio and colleagues develop a vision for combining such approaches with current edge computing technology and lifelong learning advances. The envisioned network of AI agents could quickly learn new tasks in open-ended applications, with individual AI agents independently learning and contributing to and benefiting from collective knowledge.

As the impacts of AI on everyday life increase, guidelines are needed to ensure ethical deployment and use of this technology. This is even more pressing for technology that interacts with groups that need special protection, such as children. In this Perspective Wang et al. survey the existing AI ethics guidelines with a focus on children’s issues, and provide suggestions for further development.

AI tools such as ChatGPT can provide responses to queries on any topic, but can such large language models accurately ‘write’ molecules as output to our specification? Results now show that models trained on general text can be tweaked with small amounts of chemical data to predict molecular properties, or to design molecules based on a target feature.

Training a machine learning model with multiple tasks can create more-useful representations and achieve better performance than training models for each task separately. In this Perspective, Allenspach et al. summarize and compare multi-task learning methods for computer-aided drug design.

Machine learning algorithms play important roles in medical imaging analysis but can be affected by biases in training data. Jones and colleagues discuss how causal reasoning can be used to better understand and tackle algorithmic bias in medical imaging analysis.

Recent work has demonstrated important parallels between human visual representations and those found in deep neural networks. A new study comparing functional MRI data to deep neural network models highlights factors that may determine this similarity.

Machine learning is increasingly applied for disease diagnostics due to its ability to discover differentiating features in data. However, the clinical applicability of these models remains a challenge. Pavlović et al. provide an overview of the challenges in using machine learning for biomarker discovery and suggest a causal perspective as a solution.

The implementation of particle-tracking techniques with deep neural networks is a promising way to determine particle motion within complex flow structures. A graph neural network-enhanced method enables accurate particle tracking by significantly reducing the number of lost trajectories.

New research reveals a duality between neural network weights and neuron activities that enables a geometric decomposition of the generalization gap. The framework provides a way to interpret the effects of regularization schemes such as stochastic gradient descent and dropout on generalization — and to improve upon these methods.

A framework for training artificial neural networks in physical space allows neuroscientists to build networks that look and function like real brains.

Skin-like flexible electronics (electronic skin) has great potential in medical practices to enable continuous tracking of physical and biochemical information. Xu et al. review the integration of AI methods and electronic skins, especially how data collected from sensors are processed by AI to extract features for human–machine interactions and health monitoring purposes.

Advances in machine intelligence often depend on data assimilation, but data generation has been neglected. The authors discuss mechanisms that might achieve continuous novel data generation and the creation of intelligent systems that are capable of human-like innovation, focusing on social aspects of intelligence.

Traditionally, 3D graphics involves numerical methods for physical and virtual simulations of real-world scenes. Spielberg et al. review how deep learning enables differentiable visual computing, which determines how graphics outputs change when the environment changes, with applications in areas such as computer-aided design, manufacturing and robotics.

Recommender systems are a predominant feature of online platforms and one of the most widespread applications of artificial intelligence. A new model captures information dynamics driven by algorithmic recommendations and offers ways to ensure that users are exposed to diverse content and information.

New algorithms allow researchers to decode words the brain is hearing with a non-invasive method, outside the scalp.

Efficient quantum-control protocols are required to utilize the full power of quantum computers. A new reinforcement learning approach can realize efficient, robust control of quantum many-body states, promising a practical advance in harnessing present-day quantum technologies.

Limited interpretability and understanding of machine learning methods in healthcare hinder their clinical impact. Imrie et al. discuss five types of machine learning interpretability. They examine medical stakeholders, highlight how interpretability meets their needs and emphasize the role of tailored interpretability in linking machine learning advancements to clinical impact.

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