Early and accurate pneumonia detection from chest X-rays (CXRs) is clinically critical to expedite treatment and isolation, reduce complications, and curb unnecessary antibiotic use. Although artificial intelligence (AI) substantially improves CXR-based detection, development is hindered by globally distributed data, high inter-hospital variability, and strict privacy regulations (e.g., HIPAA, GDPR) that make centralization impractical. These constraints are compounded by heterogeneous imaging protocols, uneven data availability, and the costs of transferring large medical images across geographically dispersed sites. In this paper, we evaluate Federated Learning (FL) using the Sherpa.ai FL platform, enabling multiple hospitals (nodes) to collaboratively train a CXR classifier for pneumonia while keeping data in place and private. Using the Pediatric Pneumonia Chest X-ray dataset, we simulate cross-hospital collaboration with non-independent and non-identically distributed (non-IID) data, reproducing real-world variability across institutions and jurisdictions. Our experiments demonstrate that collaborative and privacy-preserving training across multiple hospitals via FL led to a dramatic performance improvement achieving 0.900 Accuracy and 0.966 ROC-AUC, corresponding to 47.5% and 50.0% gains over single-hospital models (0.610; 0.644), without transferring any patient CXR. These results indicate that FL delivers high-performing, generalizable, secure and private pneumonia detection across healthcare networks, with data kept local. This is especially relevant for rare diseases, where FL enables secure multi-institutional collaboration without data movement, representing a breakthrough for accelerating diagnosis and treatment development in low-data domains.

Recently, large language models (LLMs) have achieved widespread application across various fields. Despite their impressive capabilities, LLMs suffer from a lack of structured reasoning ability, particularly for complex tasks requiring domain-specific best practices, which are often unavailable in the training data. Although multi-step prompting methods incorporating human best practices, such as chain-of-thought and tree-of-thought, have gained popularity, they lack a general mechanism to control LLM behavior. In this paper, we propose SHERPA, a model-driven framework to improve the LLM performance on complex tasks by explicitly incorporating domain-specific best practices into hierarchical state machines. By structuring the LLM execution processes using state machines, SHERPA enables more fine-grained control over their behavior via rules or decisions driven by machine learning-based approaches, including LLMs. We show that SHERPA is applicable to a wide variety of tasks-specifically, code generation, class name generation, and question answering-replicating previously proposed approaches while further improving the performance. We demonstrate the effectiveness of SHERPA for the aforementioned tasks using various LLMs. Our systematic evaluation compares different state machine configurations against baseline approaches without state machines. Results show that integrating well-designed state machines significantly improves the quality of LLM outputs, and is particularly beneficial for complex tasks with well-established human best practices but lacking data used for training LLMs.

Foundation models (FMs) such as large language models have revolutionized the field of AI by showing remarkable performance in various tasks. However, they exhibit numerous limitations that prevent their broader adoption in many real-world systems, which often require a higher bar for trustworthiness and usability. Since FMs are trained using loss functions aimed at reconstructing the training corpus in a self-supervised manner, there is no guarantee that the model's output aligns with users' preferences for a specific task at hand. In this survey paper, we propose a conceptual framework that encapsulates different modes by which agents could interact with FMs and guide them suitably for a set of tasks, particularly through knowledge augmentation and reasoning. Our framework elucidates agent role categories such as updating the underlying FM, assisting with prompting the FM, and evaluating the FM output. We also categorize several state-of-the-art approaches into agent interaction protocols, highlighting the nature and extent of involvement of the various agent roles. The proposed framework provides guidance for future directions to further realize the power of FMs in practical AI systems.

Precision phenomenological studies of high-multiplicity scattering processes at collider experiments present a substantial theoretical challenge and are vitally important ingredients in experimental measurements. Machine learning technology has the potential to dramatically optimise simulations for complicated final states. We investigate the use of neural networks to approximate matrix elements, studying the case of loop-induced diphoton production through gluon fusion. We train neural network models on one-loop amplitudes from the NJet C++ library and interface them with the Sherpa Monte Carlo event generator to provide the matrix element within a realistic hadronic collider simulation. Computing some standard observables with the models and comparing to conventional techniques, we find excellent agreement in the distributions and a reduced total simulation time by a factor of thirty.

Indonesian healthcare superapp Alodokter provides end-to-end digital solutions to patients including telemedicine, doctor bookings, medical content, and health-insurance services. It has more than 28 million monthly active users, and more than 40,000 certified doctors on the platform. Perhaps unsurprisingly, Alodokter found that engagement was high when users were unwell, but that it was difficult to keep people active on the app otherwise. It also found that it had a retention problem, with a lot of uninstalls happening almost immediately after installation. Alodokter's marketing goals were three-fold: increase app engagement to reduce churn and boost retention, increase active users across the app, and improve conversion and clickthrough rates (CVRs and CTRs) of push campaigns to uplift engagement.

Founder and CEO of Sherpa.ai Running into the person I like during a town festival or having dinner with my friends, until late into the night, makes me happier than any entrepreneurial success. These types of affirmations, which are hard for many of us to admit, describe the nature of the "moments" that make us happy. Of course, we all have responsibilities and obligations, and can't always enjoy those moments. But aside from that, or rather, due to the restrictions, the circumstances that make those "moments" happen cannot take place.

Natural language processing expert system: the system integrates five levels of linguistically-motivated processing to arrive at an unambiguous representation of the user's intent. Sherpa's technology is able to represent the meaning expressed through language in a conceptual, language-independent way, at an abstract level that is separate from any specific language. The engine is able to arrive at the correct analysis of ambiguous inputs by applying constraints during the analysis process that rule out all but the intended meaning, eliminating unlikely or impossible interpretations. A language-independent conceptual representation is referred to as an Interlingua. As a consequence, the time required to add a new language to Sherpa's set of supported languages is exponentially reduced. The core Sherpa system includes over 300,000 concepts and 5,000 syntactical and semantic rules, as well as the large dictionaries required to support these concepts.

The high demand of artificial intelligence services at the edges that also preserve data privacy has pushed the research on novel machine learning paradigms that fit those requirements. Federated learning has the ambition to protect data privacy through distributed learning methods that keep the data in their data silos. Likewise, differential privacy attains to improve the protection of data privacy by measuring the privacy loss in the communication among the elements of federated learning. The prospective matching of federated learning and differential privacy to the challenges of data privacy protection has caused the release of several software tools that support their functionalities, but they lack of the needed unified vision for those techniques, and a methodological workflow that support their use. Hence, we present the Sherpa.ai Federated Learning framework that is built upon an holistic view of federated learning and differential privacy. It results from the study of how to adapt the machine learning paradigm to federated learning, and the definition of methodological guidelines for developing artificial intelligence services based on federated learning and differential privacy. We show how to follow the methodological guidelines with the Sherpa.ai Federated Learning framework by means of a classification and a regression use cases.

Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks. With Sherpa, scientists can quickly optimize hyperparameters using a variety of powerful and interchangeable algorithms. Sherpa can be run on either a single machine or in parallel on a cluster. Finally, an interactive dashboard enables users to view the progress of models as they are trained, cancel trials, and explore which hyperparameter combinations are working best. Sherpa empowers machine learning practitioners by automating the more tedious aspects of model tuning. Its source code and documentation are available at https://github.com/sherpa-ai/sherpa.

Sherpa.ai offers advanced Artificial Intelligence Technology to empower your organization, improving efficiency and automation, boosting customer satisfaction, and increasing revenue through better decision-making.