A5057195145- Face and Expression Recognition
- Artificial Intelligence in Healthcare and Education
- Artificial Intelligence in Games
- Sports Analytics and Performance
- Image Retrieval and Classification Techniques
- Machine Learning in Healthcare
- Advanced Image and Video Retrieval Techniques
- Data Management and Algorithms
- Topic Modeling
- Explainable Artificial Intelligence (XAI)
- Anomaly Detection Techniques and Applications
- Advanced Clustering Algorithms Research
- Ethics and Social Impacts of AI
- Time Series Analysis and Forecasting
- Sepsis Diagnosis and Treatment
- Machine Learning and Data Classification
- Retinal Imaging and Analysis
- Data Mining Algorithms and Applications
- Text and Document Classification Technologies
- Multimodal Machine Learning Applications
- Remote-Sensing Image Classification
- Reinforcement Learning in Robotics
- COVID-19 epidemiological studies
- Retinal Diseases and Treatments
- Healthcare cost, quality, practices
DeepMind (United Kingdom)
2016-2025
Google (United States)
2022-2025
Google (United Kingdom)
2016-2024
Mind
2024
University of Oxford
2022
Jožef Stefan International Postgraduate School
2012-2016
Jožef Stefan Institute
2009-2015
University of Novi Sad
2007
Abstract Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess knowledge of typically rely on automated evaluations based limited benchmarks. Here, address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries new dataset questions searched online, HealthSearchQA. We propose human...
The practice of mathematics involves discovering patterns and using these to formulate prove conjectures, resulting in theorems. Since the 1960s, mathematicians have used computers assist discovery formulation conjectures1, most famously Birch Swinnerton-Dyer conjecture2, a Millennium Prize Problem3. Here we provide examples new fundamental results pure that been discovered with assistance machine learning-demonstrating method by which learning can aid conjectures We propose process discover...
Recent artificial intelligence (AI) systems have reached milestones in "grand challenges" ranging from Go to protein-folding. The capability retrieve medical knowledge, reason over it, and answer questions comparably physicians has long been viewed as one such grand challenge. Large language models (LLMs) catalyzed significant progress question answering; Med-PaLM was the first model exceed a "passing" score US Medical Licensing Examination (USMLE) style with of 67.2% on MedQA dataset....
Introduction Standards for Reporting of Diagnostic Accuracy Study (STARD) was developed to improve the completeness and transparency reporting in studies investigating diagnostic test accuracy. However, its current form, STARD 2015 does not address issues challenges raised by artificial intelligence (AI)-centred interventions. As such, we propose an AI-specific version checklist (STARD-AI), which focuses on AI accuracy studies. This paper describes methods that will be used develop STARD-AI....
We analyze the knowledge acquired by AlphaZero, a neural network engine that learns chess solely playing against itself yet becomes capable of outperforming human players. Although system trains without access to games or guidance, it appears learn concepts analogous those used provide two lines evidence. Linear probes applied AlphaZero's internal state enable us quantify when and where such are represented in network. also describe behavioral analysis opening play, including qualitative...
At the heart of medicine lies physician-patient dialogue, where skillful history-taking paves way for accurate diagnosis, effective management, and enduring trust. Artificial Intelligence (AI) systems capable diagnostic dialogue could increase accessibility, consistency, quality care. However, approximating clinicians' expertise is an outstanding grand challenge. Here, we introduce AMIE (Articulate Medical Explorer), a Large Language Model (LLM) based AI system optimized dialogue. uses novel...
Excellence in a wide variety of medical applications poses considerable challenges for AI, requiring advanced reasoning, access to up-to-date knowledge and understanding complex multimodal data. Gemini models, with strong general capabilities long-context offer exciting possibilities medicine. Building on these core strengths Gemini, we introduce Med-Gemini, family highly capable models that are specialized medicine the ability seamlessly use web search, can be efficiently tailored novel...
Large language models (LLMs) have shown promise in medical question answering, with Med-PaLM being the first to exceed a 'passing' score United States Medical Licensing Examination style questions. However, challenges remain long-form answering and handling real-world workflows. Here, we present 2, which bridges these gaps combination of base LLM improvements, domain fine-tuning new strategies for improving reasoning grounding through ensemble refinement chain retrieval. 2 scores up 86.5% on...
Abstract Identifying key patterns of tactics implemented by rival teams, and developing effective responses, lies at the heart modern football. However, doing so algorithmically remains an open research challenge. To address this unmet need, we propose TacticAI, AI football assistant developed evaluated in close collaboration with domain experts from Liverpool FC. We focus on analysing corner kicks, as they offer coaches most direct opportunities for interventions improvements. TacticAI...
Abstract At the heart of medicine lies physician–patient dialogue, where skillful history-taking enables effective diagnosis, management and enduring trust 1,2 . Artificial intelligence (AI) systems capable diagnostic dialogue could increase accessibility quality care. However, approximating clinicians’ expertise is an outstanding challenge. Here we introduce AMIE (Articulate Medical Intelligence Explorer), a large language model (LLM)-based AI system optimized for dialogue. uses...
High-dimensional data arise naturally in many domains, and have regularly presented a great challenge for traditional mining techniques, both terms of effectiveness efficiency. Clustering becomes difficult due to the increasing sparsity such data, as well difficulty distinguishing distances between points. In this paper, we take novel perspective on problem clustering high-dimensional data. Instead attempting avoid curse dimensionality by observing lower dimensional feature subspace, embrace...
Advances in algorithmic fairness have largely omitted sexual orientation and gender identity. We explore queer concerns privacy, censorship, language, online safety, health, employment to study the positive negative effects of artificial intelligence on communities. These issues underscore need for new directions research that take into account a multiplicity considerations, from privacy preservation, context sensitivity process fairness, an awareness sociotechnical impact increasingly...
Abstract Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. An important step characterize the (un)fairness of ML models—their tendency perform differently across subgroups population—and understand underlying mechanisms. One potential driver algorithmic unfairness, shortcut learning, arises when models base predictions on improper correlations in training data. Diagnosing this...
This paper focuses on the opportunities and ethical societal risks posed by advanced AI assistants. We define assistants as artificial agents with natural language interfaces, whose function is to plan execute sequences of actions behalf a user, across one or more domains, in line user's expectations. The starts considering technology itself, providing an overview assistants, their technical foundations potential range applications. It then explores questions around value alignment,...
Large language models (LLMs) have demonstrated impressive capabilities in natural understanding and generation, but the quality bar for medical clinical applications is high. Today, attempts to assess models' knowledge typically rely on automated evaluations limited benchmarks. There no standard evaluate model predictions reasoning across a breadth of tasks. To address this, we present MultiMedQA, benchmark combining six existing open question answering datasets spanning professional exams,...
Most machine-learning tasks, including classification, involve dealing with high-dimensional data. It was recently shown that the phenomenon of hubness, inherent to data, can be exploited improve methods based on nearest neighbors (NNs). Hubness refers emergence points (hubs) appear among k NNs many other in and constitute influential for kNN classification. In this paper, we present a new probabilistic approach naive hubness Bayesian k-nearest neighbor (NHBNN), which employs computing class...