Explore the vast range of titles available.

Machine learning (ML) has become a vital part in many aspects of our daily life. However, building well performing machine learning applications requires highly specialized data scientists and domain experts. Automated machine learning (AutoML) aims to reduce the demand for data scientists by enabling domain experts to build machine learning applications automatically without extensive knowledge of statistics and machine learning. This paper is a combination of a survey on current AutoML methods and a benchmark of popular AutoML frameworks on real data sets. Driven by the selected frameworks for evaluation, we summarize and review important AutoML techniques and methods concerning every step in building an ML pipeline. The selected AutoML frameworks are evaluated on 137 data sets from established AutoML benchmark suites.

Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result in them making plausible but incorrect statements 1 , 2 . This hinders the use of current large models in scientific discovery. Here we introduce FunSearch (short for searching in the function space), an evolutionary procedure based on pairing a pretrained LLM with a systematic evaluator. We demonstrate the effectiveness of this approach to surpass the best-known results in important problems, pushing the boundary of existing LLM-based approaches 3 . Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we discover new constructions of large cap sets going beyond the best-known ones, both in finite dimensional and asymptotic cases. This shows that it is possible to make discoveries for established open problems using LLMs. We showcase the generality of FunSearch by applying it to an algorithmic problem, online bin packing, finding new heuristics that improve on widely used baselines. In contrast to most computer search approaches, FunSearch searches for programs that describe how to solve a problem, rather than what the solution is. Beyond being an effective and scalable strategy, discovered programs tend to be more interpretable than raw solutions, enabling feedback loops between domain experts and FunSearch, and the deployment of such programs in real-world applications. FunSearch makes discoveries in established open problems using large language models by searching for programs describing how to solve a problem, rather than what the solution is.

Researchers are defining new types of interactions between humans and machine learning algorithms generically called human-in-the-loop machine learning. Depending on who is in control of the learning process, we can identify: active learning, in which the system remains in control; interactive machine learning, in which there is a closer interaction between users and learning systems; and machine teaching, where human domain experts have control over the learning process. Aside from control, humans can also be involved in the learning process in other ways. In curriculum learning human domain experts try to impose some structure on the examples presented to improve the learning; in explainable AI the focus is on the ability of the model to explain to humans why a given solution was chosen. This collaboration between AI models and humans should not be limited only to the learning process; if we go further, we can see other terms that arise such as Usable and Useful AI. In this paper we review the state of the art of the techniques involved in the new forms of relationship between humans and ML algorithms. Our contribution is not merely listing the different approaches, but to provide definitions clarifying confusing, varied and sometimes contradictory terms; to elucidate and determine the boundaries between the different methods; and to correlate all the techniques searching for the connections and influences between them.

Recent breakthroughs in artificial intelligence (AI) are increasingly driven by systems orchestrating multiple large language models (LLMs) and other specialized tools, such as search engines and simulators. So far, these systems are primarily handcrafted by domain experts and tweaked through heuristics rather than being automatically optimized, presenting a substantial challenge to accelerating progress. The development of artificial neural networks faced a similar challenge until backpropagation and automatic differentiation transformed the field by making optimization turnkey. Analogously, here we introduce TextGrad, a versatile framework that performs optimization by backpropagating LLM-generated feedback to improve AI systems. By leveraging natural language feedback to critique and suggest improvements to any part of a system—from prompts to outputs such as molecules or treatment plans—TextGrad enables the automatic optimization of generative AI systems across diverse tasks. We demonstrate TextGrad’s generality and effectiveness through studies in solving PhD-level science problems, optimizing plans for radiotherapy treatments, designing molecules with specific properties, coding, and optimizing agentic systems. TextGrad empowers scientists and engineers to easily develop impactful generative AI systems. Generative artificial intelligence (AI) systems can be optimized using TextGrad, a framework that performs optimization by backpropagating large-language-model-generated feedback; TextGrad enables optimization across diverse tasks, including radiotherapy treatment plans and molecule generation.

Systematic scientometric reviews, empowered by computational and visual analytic approaches, offer opportunities to improve the timeliness, accessibility, and reproducibility of studies of the literature of a field of research. On the other hand, effectively and adequately identifying the most representative body of scholarly publications as the basis of subsequent analyses remains a common bottleneck in the current practice. What can we do to reduce the risk of missing something potentially significant? How can we compare different search strategies in terms of the relevance and specificity of topical areas covered? In this study, we introduce a flexible and generic methodology based on a significant extension of the general conceptual framework of citation indexing for delineating the literature of a research field. The method, through cascading citation expansion, provides a practical connection between studies of science from local and global perspectives. We demonstrate an application of the methodology to the research of literature-based discovery (LBD) and compare five datasets constructed based on three use scenarios and corresponding retrieval strategies, namely a query-based lexical search (one dataset), forward expansions starting from a groundbreaking article of LBD (two datasets), and backward expansions starting from a recently published review article by a prominent expert in LBD (two datasets). We particularly discuss the relevance of areas captured by expansion processes with reference to the query-based scientometric visualization. The method used in this study for comparing bibliometric datasets is applicable to comparative studies of search strategies.

Advances in machine learning (ML) and artificial intelligence (AI) present an opportunity to build better tools and solutions to help address some of the world’s most pressing challenges, and deliver positive social impact in accordance with the priorities outlined in the United Nations’ 17 Sustainable Development Goals (SDGs). The AI for Social Good (AI4SG) movement aims to establish interdisciplinary partnerships centred around AI applications towards SDGs. We provide a set of guidelines for establishing successful long-term collaborations between AI researchers and application-domain experts, relate them to existing AI4SG projects and identify key opportunities for future AI applications targeted towards social good. The AI for Social Good movement aims to apply AI/ML tools to help in delivering on the United Nations’ sustainable development goals (SDGs). Here, the authors identify the challenges and propose guidelines for designing and implementing successful partnerships between AI researchers and application - domain experts.

Identifying key patterns of tactics implemented by rival teams, and developing effective responses, lies at the heart of modern football. However, doing so algorithmically remains an open research challenge. To address this unmet need, we propose TacticAI, an AI football tactics assistant developed and evaluated in close collaboration with domain experts from Liverpool FC. We focus on analysing corner kicks, as they offer coaches the most direct opportunities for interventions and improvements. TacticAI incorporates both a predictive and a generative component, allowing the coaches to effectively sample and explore alternative player setups for each corner kick routine and to select those with the highest predicted likelihood of success. We validate TacticAI on a number of relevant benchmark tasks: predicting receivers and shot attempts and recommending player position adjustments. The utility of TacticAI is validated by a qualitative study conducted with football domain experts at Liverpool FC. We show that TacticAI’s model suggestions are not only indistinguishable from real tactics, but also favoured over existing tactics 90% of the time, and that TacticAI offers an effective corner kick retrieval system. TacticAI achieves these results despite the limited availability of gold-standard data, achieving data efficiency through geometric deep learning. In modern football games, data-driven analysis serves as a key driver in determining tactics. Wang, Veličković, Hennes et al. develop a geometric deep learning algorithm, named TacticAI, to solve high-dimensional learning tasks over corner kicks and suggest tactics favoured over existing ones 90% of the time.

Systems that can learn interactively from their end‐users are quickly becoming widespread. Until recently, this progress has been fueled mostly by advances in machine learning; however, more and more researchers are realizing the importance of studying users of these systems. In this article we promote this approach and demonstrate how it can result in better user experiences and more effective learning systems. We present a number of case studies that demonstrate how interactivity results in a tight coupling between the system and the user, exemplify ways in which some existing systems fail to account for the user, and explore new ways for learning systems to interact with their users. After giving a glimpse of the progress that has been made thus far, we discuss some of the challenges we face in moving the field forward.

Artificial intelligence (AI) provides considerable opportunities to assist human work. However, one crucial challenge of human–AI collaboration is that many AI algorithms operate in a black-box manner where the way how the AI makes predictions remains opaque. This makes it difficult for humans to validate a prediction made by AI against their own domain knowledge. For this reason, we hypothesize that augmenting humans with explainable AI improves task performance in human–AI collaboration. To test this hypothesis, we implement explainable AI in the form of visual heatmaps in inspection tasks conducted by domain experts. Visual heatmaps have the advantage that they are easy to understand and help to localize relevant parts of an image. We then compare participants that were either supported by (a) black-box AI or (b) explainable AI, where the latter supports them to follow AI predictions when the AI is accurate or overrule the AI when the AI predictions are wrong. We conducted two preregistered experiments with representative, real-world visual inspection tasks from manufacturing and medicine. The first experiment was conducted with factory workers from an electronics factory, who performed assessments of whether electronic products have defects. The second experiment was conducted with radiologists, who performed assessments of chest X-ray images to identify lung lesions. The results of our experiments with domain experts performing real-world tasks show that task performance improves when participants are supported by explainable AI with heatmaps instead of black-box AI. We find that explainable AI as a decision aid improved the task performance by 7.7 percentage points (95% confidence interval [CI]: 3.3% to 12.0%, ) in the manufacturing experiment and by 4.7 percentage points (95% CI: 1.1% to 8.3%, ) in the medical experiment compared to black-box AI. These gains represent a significant improvement in task performance.

Recent advancements in Explainable Artificial Intelligence (XAI) aim to bridge the gap between complex artificial intelligence (AI) models and human understanding, fostering trust and usability in AI systems. However, challenges persist in comprehensively interpreting these models, hindering their widespread adoption. This study addresses these challenges by exploring recently emerging techniques in XAI. The primary problem addressed is the lack of transparency and interpretability in AI models to humanity for institution-wide use, which undermines user trust and inhibits their integration into critical decision-making processes. Through an in-depth review, this study identifies the objectives of enhancing the interpretability of AI models and improving human understanding of their decision-making processes. Various methodological approaches, including post-hoc explanations, model transparency methods, and interactive visualization techniques, are investigated to elucidate AI model behaviours. We further present techniques and methods to make AI models more interpretable and understandable to humans including their strengths and weaknesses to demonstrate promising advancements in model interpretability, facilitating better comprehension of complex AI systems by humans. In addition, we provide the application of XAI in local use cases. Challenges, solutions, and open research directions were highlighted to clarify these compelling XAI utilization challenges. The implications of this research are profound, as enhanced interpretability fosters trust in AI systems across diverse applications, from healthcare to finance. By empowering users to understand and scrutinize AI decisions, these techniques pave the way for more responsible and accountable AI deployment.