Relevant bibliographies by topics / AI in Discovery

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers
  6. Reports

Academic literature on the topic 'AI in Discovery'

Author: Grafiati
Published: 7 June 2025
Last updated: 16 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'AI in Discovery.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "AI in Discovery"

1

Laddha, C. S., A. V. Shelke, Y. V. Vaidya, A. A. Sheikh, and K. R. Biyani. "A Review on Artificial Intellegence in Drug Discovery & Pharmaceutical Industry." Asian Journal of Pharmaceutical Research and Development 11, no. 3 (2023): 45–51. http://dx.doi.org/10.22270/ajprd.v11i3.1252.

Full text
Abstract:
Introduction: The use of artificial intelligence (AI) in drug discovery and the pharma industry has been rapidly expanding in recent years. AI algorithms can analyze vast amounts of data, identify patterns, and make predictions that can accelerate drug discovery and improve patient outcomes.
 Methods: AI is being used in various stages of the drug discovery process, from target identification and lead optimization to clinical trials and post-market surveillance. Machine learning algorithms, neural networks, and natural language processing are among the AI techniques used in drug discovery.
 Results: AI-based drug discovery has already shown promising results, with several drugs in clinical trials or approved for use that were discovered using AI. AI is also being used to improve clinical trial design and patient selection, as well as to monitor adverse drug events and optimize drug dosing.
 Conclusion: AI has the potential to transform the drug discovery and pharma industry, making drug development faster, more efficient, and more effective. However, there are still challenges that need to be addressed, such as the need for high-quality data and the potential for bias in AI algorithms. Overall, the use of AI in drug discovery and the pharma industry is an exciting and rapidly evolving field that has the potential to improve patient outcomes and revolutionize healthcare.
APA, Harvard, Vancouver, ISO, and other styles
2

Tsunoyama, Kazuhisa. "AI and drug discovery." Proceedings for Annual Meeting of The Japanese Pharmacological Society 92 (2019): 3—CS4–1. http://dx.doi.org/10.1254/jpssuppl.92.0_3-cs4-1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Boomisha, S. D.* Jemmy Christy H. "AI in Drug Discovery." International Journal of Pharmaceutical Sciences 3, no. 2 (2025): 1800–1810. https://doi.org/10.5281/zenodo.14907864.

Full text
Abstract:
Artificial intelligence (AI) is the technology and science of creating intelligent machines by using algorithms which the machine adheres to in order to mimic human cognitive functions like learning and problem solving. Artificial intelligence (AI) is the term used to describe computer programs that simulate the mechanisms that support the intellect of humans, including as engagement, deep learning, reasoning, adaptation, and sensory comprehension. It aims to mimic human cognitive functions. This article examines the prospective applications of AI in drug discovery, emphasizing significant developments and their possible effects. Target identification is being expedited by AI-driven predictive modeling, which is also expediting the identification of prospective medication candidates. An expedient and economical substitute for conventional drug development is provided by AI's capacity to mine data for drug repurposing. Artificial Intelligence enhances patient recruiting and trial management in clinical trials, leading to better efficiency and results. The combination of AI with large data and omics technology is yielding new insights, and in silico testing is predicting the safety and effectiveness of pharmaceuticals. Collaborative platforms driven by AI are also accelerating research and promoting open innovation. This paper highlights the enormous influence artificial intelligence (AI) is expected to have on drug discovery, with the potential to produce novel and efficient treatments that would significantly improve global healthcare.
APA, Harvard, Vancouver, ISO, and other styles
4

Rama, Brahma Reddy D.* Malleswari K. Chetan M. Adarsh Babu B. Bhuvan Chandra Durga Eswar J. "A Review On Role Of Artificial Intelligence In Drug Discovery." International Journal of Pharmaceutical Sciences 2, no. 8 (2024): 2913–22. https://doi.org/10.5281/zenodo.13293031.

Full text
Abstract:
Artificial intelligence accelerates the drug discovery and development process and reduces the cost, with enormous amounts of successful applications from language modeling to improvement in the pharmaceutical sector. The deep-learning approach has been used throughout the drug discovery steps as the drug-related data increase. In this mini-review, I gave a general description of AI and its application in drug discovery and development. Computer-aided drug discovery and ligand-based quantitative structure activity and property (QSAR/ QSPR) and De Novo drug design, integration with single cell technology, drug metabolism, and excretion, and discuss recent advancement in colorectal cancer and tooth loss, integration of plant-based traditional medicine, and showing AI-assisted platform used to discover serotonin 5-HT1A drug, which is reaching the clinical trial in less than 12 months which is far less than conventional method that needs four years of drug discovery process.
APA, Harvard, Vancouver, ISO, and other styles
5

Abhishek, Sahu* Prem Samundre Dr. Jitendra Banweer. "AI in Drug Discovery and Development." International Journal of Pharmaceutical Sciences 3, no. 5 (2025): 2510–15. https://doi.org/10.5281/zenodo.15426727.

Full text
Abstract:
Artificial intelligence (AI) is revolutionizing the landscape of drug discovery and development by accelerating timelines, reducing costs, and improving the precision of therapeutic design. From target identification to lead optimization and clinical trial design, AI-driven approaches—such as machine learning, deep learning, and natural language processing—are enhancing the efficiency and predictive power of each stage in the pharmaceutical pipeline. This review explores the current applications of AI across the drug development lifecycle, with a focus on virtual screening, de novo drug design, biomarker discovery, and patient stratification. We also discuss the challenges and limitations of integrating AI into biomedical research, including data quality, model interpretability, and regulatory considerations. By highlighting recent breakthroughs and emerging trends, this paper underscores the transformative potential of AI to redefine how new drugs are discovered, tested, and brought to market. 
APA, Harvard, Vancouver, ISO, and other styles
6

Varun, Ahuja. "Artificial Intelligence (AI) in Drug Discovery and Medicine." Journal of Clinical Cases & Reports 2, no. 3 (2019): 76–80. http://dx.doi.org/10.46619/joccr.2019.2-1043.

Full text
Abstract:
Artificial intelligence (AI) is a branch of computer science that deals with the development of algorithms that seek to simulate human intelligence. The phrase “artificial intelligence” was likely coined during a conference at Dartmouth College in 1956. The earliest work of medical AI dates back to the early 1970s. Over years, AI has found implications in various fields. In this article, we summarize its applications in drug discovery and medicine.
APA, Harvard, Vancouver, ISO, and other styles
7

LeCun, Yann. "Artificial Intelligence in Scientific Research: Transforming Data Analysis and Discovery." International Journal of Innovative Computer Science and IT Research 1, no. 01 (2025): 1–9. https://doi.org/10.63665/ijicsitr.v1i01.01.

Full text
Abstract:
Artificial Intelligence (AI) has become a transformative tool in scientific research, reshaping traditional methodologies by enabling advanced data analysis, hypothesis testing, and predictive modeling. The integration of machine learning (ML), deep learning (DL), and natural language processing (NLP) has significantly accelerated discoveries in medicine, physics, chemistry, environmental science, and other disciplines. AI-driven technologies allow researchers to process large datasets, identify complex patterns, and generate predictive insights with unprecedented accuracy and speed. These innovations have led to breakthroughs in drug discovery, climate modeling, quantum physics simulations, and genetic research, demonstrating AI’s potential to enhance efficiency, automation, and precision in scientific investigations. Despite its numerous advantages, AI-driven research presents challenges, including ethical concerns, algorithmic bias, data security risks, and high computational demands. The reliance on large datasets and complex AI models raises concerns about data privacy, model transparency, and fairness in scientific conclusions. Additionally, AI systems require high-performance computing resources, making accessibility and affordability key concerns for many research institutions. Addressing these challenges through robust regulatory frameworks, ethical AI development, and improved AI model interpretability is crucial for ensuring responsible AI-driven scientific exploration. This study explores AI’s impact on scientific research, analyzing its applications, benefits, and challenges. The findings are supported by statistical data and two tables, illustrating AI’s adoption trends, efficiency improvements, and transformative role in modern research. Future advancements, such as AI-augmented automation, AI-driven robotics, and interdisciplinary AI applications, will further revolutionize scientific inquiry, making AI an indispensable tool for data-driven discovery and innovation.
APA, Harvard, Vancouver, ISO, and other styles
8

Thomas, Dan. "Revolutionising Drug Discovery." ITNOW 65, no. 2 (2023): 62–63. http://dx.doi.org/10.1093/combul/bwad068.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Beverley, Dr Charles. "Artificial Intelligence's Influence on HIV/AIDS Cure Discovery." Journal of Quality in Health Care & Economics 7, no. 1 (2024): 1–3. http://dx.doi.org/10.23880/jqhe-16000364.

Full text
Abstract:
This comprehensive review explores the transformative role of artificial intelligence (AI) in advancing research towards finding a cure for HIV/AIDS. By analyzing a diverse array of peer- reviewed articles, the review investigates how AI is revolutionizing various aspects of HIV/AIDS research, including drug discovery, treatment optimization, vaccine development, understanding HIV pathogenesis, public health interventions, and ethical considerations. Furthermore, the review discusses current challenges, future research directions, and practical implications of integrating AI into HIV/AIDS research.
APA, Harvard, Vancouver, ISO, and other styles
10

Bai, Junwen, Yexiang Xue, Johan Bjorck, et al. "Phase Mapper: Accelerating Materials Discovery with AI." AI Magazine 39, no. 1 (2018): 15–26. http://dx.doi.org/10.1609/aimag.v39i1.2785.

Full text
Abstract:
From the stone age, to the bronze, iron age, and modern silicon age, the discovery and characterization of new materials has always been instrumental to humanity's progress and development. With the current pressing need to address sustainability challenges and find alternatives to fossil fuels, we look for solutions in the development of new materials that will allow for renewable energy. To discover materials with the required properties, materials scientists can perform high-throughput materials discovery, which includes rapid synthesis and characterization via X-ray diffraction (XRD) of thousands of materials. A central problem in materials discovery, the phase map identification problem, involves the determination of the crystal structure of materials from materials composition and structural characterization data. This analysis is traditionally performed mainly by hand, which can take days for a single material system. In this work we present Phase-Mapper, a solution platform that tightly integrates XRD experimentation, AI problem solving, and human intelligence for interpreting XRD patterns and inferring the crystal structures of the underlying materials. Phase-Mapper is compatible with any spectral demixing algorithm, including our novel solver, AgileFD, which is based on convolutive non-negative matrix factorization. AgileFD allows materials scientists to rapidly interpret XRD patterns, and incorporates constraints to capture prior knowledge about the physics of the materials as well as human feedback. With our system, materials scientists have been able to interpret previously unsolvable systems of XRD data at the Department of Energy’s Joint Center for Artificial Photosynthesis, including the Nb-Mn-V oxide system, which led to the discovery of new solar light absorbers and is provided as an illustrative example of AI-enabled high throughput materials discovery
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "AI in Discovery"

1

Kacher, Yulia. "AI-Driven Discovery of Voltage-Gated Ion Channels’ Intermediate States." Electronic Thesis or Diss., Université de Lorraine, 2024. http://www.theses.fr/2024LORR0227.

Full text
Abstract:
Les canaux ioniques dépendants du voltage (VGICs) jouent un rôle crucial dans de nombreux processus physiologiques, y compris la transmission des impulsions nerveuses et la contraction musculaire. Ils sont également des cibles majeures en développement pharmaceutique, représentant environ 20 % des cibles de petites molécules, particulièrement pour les maladies comme l'épilepsie, les arythmies et autres canalopathies. Malgré les progrès significatifs de la microscopie cryo-électronique fournissant des détails structuraux approfondis, la capture des états intermédiaires dynamiques pendant les transitions de verrouillage des VGIC reste un défi. Ces conformations intermédiaires, qui existent entre les états ouvert et fermé, sont cruciales pour comprendre les propriétés de verrouillage uniques de chaque canal. Cependant, leur nature transitoire les rend difficiles à capturer par les techniques conventionnelles. Les simulations de dynamique moléculaire offrent une solution potentielle en modélisant ces transitions, mais elles entraînent des coûts de calcul élevés et sont limitées par des barrières énergétiques restreignant l'accès aux états intermédiaires cruciaux dans des délais raisonnables. Ces défis nécessitent des approches innovantes pour explorer le paysage conformationnel des VGIC de manière plus efficace. En réponse à ces obstacles, nous avons développé une nouvelle approche basée sur l'apprentissage profond, conçue pour prédire les états intermédiaires des VGIC, en intégrant l'IA avec des connaissances basées sur la physique. Avec des données structurales des deux états opérationnels les plus distincts - ouvert et fermé - comme celles dérivées de courtes simulations de dynamique moléculaire, notre pipeline peut produire des conformations intermédiaires significatives. Notre méthode emploie un autoencodeur convolutionnel 1D servant de fonction pour réduire les données structurelles tridimensionnelles complexes en une représentation bidimensionnelle plus interprétable. Le processus inverse génère de nouvelles structures, y compris des états le long du chemin de transition. Notre approche repose sur une fonction de perte sophistiquée, intégrant l'erreur quadratique moyenne géométrique traditionnelle, des contraintes basées sur la physique issues des techniques de dynamique moléculaire, et de nouveaux termes liés aux charges de verrouillage. Ces termes sont adaptés aux VGIC, car la charge de verrouillage est reconnue comme une variable collective supérieure pour cette superfamille de protéines, garantissant des prédictions biologiquement significatives. Nous avons validé notre pipeline en utilisant des ensembles de données étendus pour le domaine du capteur de tension du canal potassique Kv1.2, dérivés de simulations de dynamique moléculaire. Le pipeline a prédit avec succès des états intermédiaires cohérents avec des recherches antérieures. De plus, les capacités du pipeline ont été étendues aux réarrangements conformationnels de canaux entiers et testées sur d'autres VGICs, notamment le canal Kv7.1 et son domaine de capteur de tension, démontrant ainsi son applicabilité large dans la recherche sur les VGIC. Cette recherche adopte une approche pluridisciplinaire, combinant bioinformatique, biologie computationnelle et prédictions pilotées par IA pour approfondir notre compréhension des mécanismes de verrouillage des VGIC. Les applications potentielles s'étendent au-delà de la biologie structurale vers la découverte de médicaments, où les connaissances sur les conformations spécifiques des VGIC pourraient orienter le développement de traitements ciblés pour les canalopathies. Globalement, ce travail représente un avancement significatif dans la recherche biologique assistée par IA, ouvrant de nouvelles voies pour explorer la fonction des VGIC et leur rôle dans les maladies<br>Voltage-gated ion channels (VGICs) are crucial for numerous physiological processes, including nerve impulse transmissionand muscle contraction, and are key targets in drug development, representing about 20% of small-molecule drug targets,particularly for diseases such as epilepsy, arrhythmias, and other channelopathies. Despite significant advancements in cryo-electronmicroscopy that provide detailed structural insights, capturing the dynamic intermediate states during VGIC gating transitions remains challenging. These intermediate conformations, which exist between the openand closed states, are crucial for understanding the unique gating properties of each channel. However, their transient nature makes them difficult to capture using conventional techniques. Molecular dynamics simulations offer a potential solution by modeling these transitions, but they come with high computational costs and are limited by energy barriers that restrict access to crucial intermediate states within feasible time frames. These challenges necessitate innovative approaches for exploring the conformational landscape of VGICs more efficiently. In response to these obstacles, we have developed a novel deeplearning-based pipeline designed to predict intermediate states in VGICs, integrating AI with physics-based insights. Given structural data for the two most distinct channel operational states - open and closed - such as those derived from shortmolecular dynamics simulations, the pipeline can produce meaningful intermediate conformations. Our approach employs a 1D convolutional autoencoder that serves as a function to reduce complex three-dimensional structural data to a more interpretable 2D representation. The reverse process generates novel structures, including states along the transition pathway. Our approach leverages a sophisticated loss function, incorporating traditional geometric mean square error, physics-based constraints derived from MD techniques, and novel gating charge-related terms. These terms are tailored to VGICs, as the gating charge is recognized as a superior collective variable for this protein superfamily, ensuring biologically meaningful predictions. We validated our pipeline using extensive datasets for the Kv1.2 potassium channel voltage sensor domain, derived from molecular dynamics simulations. The pipeline successfully predicted intermediate states consistent with prior research. Moreover, the pipeline's capabilities were extended to whole-channel conformational rearrangements and tested on other VGICs, including the Kv7.1 channel and its voltage sensor domain, demonstrating its broad applicability in VGIC research. This research employs a multi-disciplinary approach, combining bioinformatics, computational biology, and AI-driven predictions to enhance our understanding of VGIC gating mechanisms. The potential applications extend beyond structural biology into drug discovery, where insights into specific VGIC conformations could guide the development of targeted treatments for channelopathies. Overall, this work represents a significant advancement in AI-assisted biological research, providing new avenues for exploring VGIC function and their roles in disease
APA, Harvard, Vancouver, ISO, and other styles
2

Stacey, Martin Kenneth. "A model-driven approach to scientific law discovery." Thesis, University of Aberdeen, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.314674.

Full text
Abstract:
This thesis presents a structural model of one aspect of science, the theory-driven discovery of empirical laws, in terms of the knowledge structures and reasoning processes that it involves; and describes a machine learning system designed to embody the major features of the model, called OZ, which is designed to investigate the transport properties of an unknown membrane separating two solutions. Inductive data-driven discovery is an important process in science, but takes place within very tightly constrained limits defined by theoretical reasoning. An explicit specification of the possible search space for a law is a <i>law framework</i>; this takes the form of a law with some undetermined parameters. Inductive law discovery is the search for the values of these free parameters. According to the model <i>informal qualitative models</i> (IQMs) describing the essential structural features of a physical system are used to guide the selection of appropriate variables for scientific law discovery, and the selection of an appropriate mathematical function for a law. Our analysis differs from previous work in machine discovery in stressing the importance of models of internal structure in scientific discovery. OZ comprises a domain independent control structure and a set of domain independent procedures, plus a set of domain dependent heuristics for the membrane properties domain. It constructs a set of candidate IQMs for the unknown membrane, and designs goal-directed experiments to determine which IQM is the right one, generating and testing qualitative predictions about the patterns to be expected in numerical data. When it has identified a single model as correct, it constructs law frameworks for possible laws describing the transport properties of the membrane, then designs different experiments to gather data to supply to an inductive law discovery function, which looks for a law of the type specified by each law framework.
APA, Harvard, Vancouver, ISO, and other styles
3

Chen, Hongzhi. "Discovery of acoustic emission based biomarker for quantitative assessment of knee joint ageing and degeneration." Thesis, University of Central Lancashire, 2011. http://clok.uclan.ac.uk/3151/.

Full text
Abstract:
Based on the study of 34 healthy and 19 osteoarthritic knees in three different age groups (early, middle and late adulthood), this thesis reports the discovery of the potential of knee acoustic emission (AE) as a biomarker for quantitative assessment of joint ageing and degeneration. Signal processing and statistical analysis were conducted on the joint angle signals acquired using electronic goniometers attached to the lateral side of the legs during repeated sit- stand-sit movements. A four-phase movement model derived from joint angle measurement is proposed for statistical analysis, and it consists of the ascending- acceleration and ascending-deceleration phases in the sit-to- stand movement, followed by the descending-acceleration and descending-deceleration phases in the stand-to-sit movement. Through the quantitative assessment of joint angle signals based on the four-phase model established, statistical differences of different knee conditions related to age and degeneration were discovered based on cycle-by- cycle variations and movement symmetry. For AE burst signals acquired from piezo-electric sensors attached to the knee joints during repeated sit-stand-sit movements, the statistical analysis started from the quantity of AE events in the proposed four movement phases and extended to waveform features extracted from AE signals. While the quantity of AE events was found to follow certain statistical trends related to age and degeneration in each movement phase, detail statistical analysis of AE waveform features yielded the peak amplitude value and average signal level of each AE burst as two most significant features. An image based knee AE feature profile is presented based on 2D colour histograms formed by the peak amplitude value and average signal level in four movement phases. It provides not only a visual trend related to knee age and degeneration, but also enables visual assessment of the
APA, Harvard, Vancouver, ISO, and other styles
4

Hajj, hassan Houssam. "Enabling autonomous IoT systems : A middleware-based hybrid AI approach to self-adaptation." Electronic Thesis or Diss., Institut polytechnique de Paris, 2024. http://www.theses.fr/2024IPPAS029.

Full text
Abstract:
La prolifération de l'Internet des objets (IoT) a transformé les espaces traditionnels en environnements plus intelligents et interconnectés. Cela a donné lieu à des systèmes IoT sophistiqués, généralement composés de dispositifs qui détectent des phénomènes physiques et génèrent des données pouvant être traitées par des nœuds de calcul avant d'être consommées par des applications. Ces applications définissent généralement des exigences spécifiques de qualité de service (QoS) qui doivent être respectées (par exemple, disponibilité, précision, latence). À cette fin, les systèmes IoT sont souvent configurés pour garantir que les exigences de QoS des applications déployées soient respectées. Cela implique l'ajustement de plusieurs paramètres tels que les configurations réseau, les ressources de traitement, et l'optimisation des systèmes d'échange de données. Cependant, les espaces intelligents modernes sont intrinsèquement dynamiques et imprévisibles. Les variations dans le nombre de dispositifs IoT, les conditions du réseau, et les ressources de calcul disponibles créent un environnement en constante évolution. Ainsi, pour garantir que les systèmes IoT fonctionnent de manière autonome, il est essentiel de concevoir des mécanismes d'auto-adaptation pour maintenir les exigences de QoS des applications dans des situations dynamiques. Cette thèse propose une approche d'auto-adaptation à base d'intergiciel et d'intelligence artificielle (IA) hybride pour permettre des opérations autonomes des systèmes IoT dans des environnements dynamiques. En combinant des approches basées sur la logique avec des techniques d'IA basées sur les données, nous concevons des solutions d'auto-adaptation efficaces et explicables pour les systèmes IoT. Cela est réalisé à travers trois contributions principales. Tout d'abord, des réseaux de files d'attente sont utilisés pour composer des modèles de QoS qui représentent les systèmes IoT sous différentes situations et/ou configurations. En simulant ces modèles de QoS, nous sommes en mesure de générer des ensembles de données de performances qui peuvent être utilisés dans des approches auto-adaptatives pour s'adapter dynamiquement aux situations changeantes en sélectionnant la configuration qui satisfait le mieux les exigences de QoS définies par les applications. La deuxième contribution permet une gestion adaptative des flux de données pilotée par l'IA dans les espaces IoT. En combinant des techniques d'IA basées sur la logique et sur les données, telles que l'IA planning et l'apprentissage par renforcement, nous concevons un cadre impliquant des agents intelligents capables de prendre des décisions d'adaptation en temps réel. Les actions d'adaptation possibles incluent les configurations de flux de données (par exemple, priorités, taux de rejet de données) et le contrôle des ressources (par exemple, ressources réseau, ressources de calcul). Enfin, la dernière contribution permet de rendre les systèmes autonomes plus proactifs et explicables grâce à l'apprentissage par renforcement et la théorie de la causalité. Pour ce faire, nous nous appuyons sur le cadre de la causalité afin de fournir une analyse formelle des performances des systèmes IoT. Par la suite, les modèles causaux permettent un processus de prise de décision plus efficace, permettant aux agents d'adaptation de prendre des actions d'adaptation efficaces dans des environnements dynamiques. Nous validons notre approche en développant une implémentation prototype d'un système IoT et en menant des expériences sur des études de cas considérant différents types d'environnements IoT. Nos modèles de QoS sont évalués et comparés à une implémentation prototype pour valider la précision des ensembles de données de performances générés. Nous évaluons ensuite l'efficacité de notre solution en exploitant des données issues de déploiements réels pour nous assurer que notre approche est valide dans des contextes réels<br>The proliferation of Internet of Things (IoT) devices has transformed traditional spaces into smarter, more interconnected environments. These advanced IoT systems consist of devices that sense physical phenomena and generate data, which are then processed by computing nodes before being used by applications. Such applications typically define specific Quality-of-Service (QoS) requirements, such as availability, accuracy, and latency, that must be met. To achieve this, IoT systems are normally configured to ensure that the QoS requirements of the deployed applications are met. This involves adjusting multiple parameters such as network settings, processing resources, and tuning data exchange systems. However, modern smart spaces are inherently dynamic and unpredictable. Changes in the number of IoT devices, network conditions, and available computational resources create a continuously evolving environment. Thus, to ensure that IoT systems operate autonomously, it is essential to design advanced self-adaptive mechanisms for maintaining QoS requirements of applications across dynamic smart spaces.This thesis proposes a middleware-based, hybrid Artificial Intelligence (AI) self-adaptation approach for enabling autonomous IoT operations across dynamic smart spaces. By combining logic-based approaches with data-driven AI techniques, we design effective and explainable self-adaptation solutions for IoT systems operating over dynamic environments. This is achieved through three main research contributions. First, queueing network modeling techniques are leveraged to compose QoS models that represent IoT systems under different situations and/or configurations of smart spaces. By simulating QoS models, we generate performance metrics datasets that can be used as input in self-adaptive approaches. These approaches dynamically adjust to changing conditions by selecting the configuration that best meets the QoS requirements specified by the applications. The second contribution enables AI-driven adaptation of IoT systems in smart spaces. By combining AI techniques such as Automated Planning and Reinforcement Learning, we design a framework involving intelligent agents capable of taking adaptation decisions at runtime. Possible adaptation actions include data flow configurations (e.g., priorities, drop rates) and resource control (e.g., network resources, computing resources). Finally, the third contribution enables proactive and explainable autonomous systems by relying on Causal Reinforcement Learning. To achieve this, Causality methodologies are employed to provide a formal analysis of the performance of IoT systems. Subsequently, causal models enable agents to take efficient adaptation actions in dynamic environments. We validate our proposed approach by developing a prototype implementation of an IoT system and experimenting with case studies considering different types of IoT environments. Our QoS models are evaluated and compared with a prototype implementation for validating the accuracy of the generated performance metrics datasets. We then evaluate the effectiveness of our solution by leveraging data from real deployments to ensure that our approach is valid in real-life settings. The self-adaptation approach presented in this thesis can be exploited to design resilient and modern IoT systems where interactive and real-time services are required, enabling smart spaces to autonomously adapt to changes in their environment, and ensuring optimal performance even under dynamic conditions
APA, Harvard, Vancouver, ISO, and other styles
5

Rusu, Anca. "Delving into AI discourse within EU institutional communications : empowering informed decision-making for tomorrow’s tech by fostering responsible communication for emerging technologies." Electronic Thesis or Diss., Université Paris sciences et lettres, 2023. https://basepub.dauphine.fr/discover?query=%222023UPSLD029%22.

Full text
Abstract:
La prolifération des technologies émergentes, définies comme de nouvelles technologies ou de nouvelles utilisations de technologies anciennes (par exemple, l'intelligence artificielle (IA)), offre à la société à la fois des opportunités et des défis lors de leur utilisation. Ces technologies promettent de révolutionner divers secteurs en apportant de nouvelles efficacités, capacités et perspectives, ce qui les rend intéressantes à développer et à utiliser. Cependant, leur utilisation soulève également d'importantes préoccupations éthiques, environnementales et sociales. Les organisations communiquent par le biais de divers modes, dont l'un est le discours écrit. Un tel discours englobe non seulement la structure du message, mais aussi son contenu. En d'autres termes, le vocabulaire (la structure) est utilisé pour exprimer un point de vue spécifique (le contenu). Dans le domaine de l'utilisation des technologies, il existe un lien évident entre la communication et la prise de décision éclairée, car l'information sur la technologie (sa forme et sa substance) est diffusée par le biais de la communication, ce qui contribue à prendre des décisions éclairées. Cette thèse adopte une approche de gouvernance des risques, qui implique une perspective préventive visant à minimiser (ou à éviter) les risques potentiels futurs. Cette perspective reconnaît l'importance des individus prenant des décisions éclairées concernant l'acceptation ou l'action face aux risques futurs potentiels. Il convient de noter que les décisions des individus sont influencées par ce qu'ils savent sur une technologie et par leurs perceptions (ce qu'ils ne savent pas mais croient).Ainsi, notre recherche vise à explorer les perspectives théoriques sur les responsabilités de communication des organisations et les pratiques réelles employées par ces entités. Ce choix découle du manque apparent dans la littérature concernant la communication responsable et de la nécessité d'examiner ce sujet, en mettant l'accent sur les considérations pratiques pour définir davantage les modes de communication organisationnelle à analyser et à prendre des mesures proactives lors de la communication sur les technologies émergentes telles que l'IA. Lorsqu'une organisation communique sur une technologie émergente, on trouve dans la littérature des éléments mettant l'accent sur la responsabilité de partager des informations, mais aucun sur la responsabilité (considérée comme un comportement éthique) d'une organisation concernant l'impact de ce qui est communiqué sur le processus de prise de décision. Une certaine responsabilité est liée à la responsabilité sociale des entreprises (RSE), mais l'accent reste sur l'information. Nous proposons un concept qui aborde l'intersection entre trois domaines considérés : les technologies émergentes, la communication organisationnelle et la gouvernance des risques, à savoir celui de la Communication Organisationnelle Responsable sur les Technologies Émergentes (ROCET) pour aborder la responsabilité de ce qui est communiqué en tant que comportement éthique. Nous visons à approfondir ce concept en comblant le fossé entre la théorie et la pratique, en examinant les deux simultanément pour obtenir une compréhension globale. Deux analyses seront menées en parallèle : une revue critique de la littérature autour du concept de "communication responsable" et une analyse de discours de rapports autonomes publiés par des organismes gouvernementaux concernant l'utilisation d'une technologie émergente spécifique, à savoir l'intelligence artificielle (IA). La littérature se concentre soit sur la communication menée par les organisations dans le cadre de leur stratégie de responsabilité sociale, soit du point de vue de la théorie de la communication, en se concentrant sur la manière de transmettre efficacement un message<br>The proliferation of emerging technologies, which are defined as new technologies or new use of old technologies (for example, artificial intelligence (AI)), presents both opportunities and challenges for society when used. These technologies promise to revolutionize various sectors, providing new efficiencies, capabilities, and insights, which makes them interesting to develop and use. However, their use also raises significant ethical, environmental, and social concerns. Organizations communicate through various modes, one of which is written discourse. Such discourse encompasses not only the structure of the message but also its content. In other words, the vocabulary (the structure) is used to express a specific point of view (the content). Within technology usage, there is a clear connection between communication and informed decision-making, as the information about the technology (its form and substance) is spread through communication, which in turn aids in making well-informed decisions. This thesis adopts a risk governance approach, which involves taking a preventive perspective to minimize (or avoid) future potential risks. This viewpoint acknowledges the importance of people making informed decisions about accepting or acting in light of potential future risks. It is to be noted that people's decisions are influenced by what they know about a technology and their perceptions (what they do not know but believe). Hence, our research aims to explore the theoretical perspectives on organizations' communication responsibilities and the actual practices employed by these entities. This choice stems from the apparent gap in the literature concerning responsible communication and the necessity to examine the topic, emphasizing practical considerations for further defining modes of organizational communication to analyze and take proactive action when communicating about emerging technologies such as AI. When an organization communicates about an emerging technology, elements focusing on the responsibility of sharing information can be found in the literature, but none on the responsibility (seen as an ethical behavior) of one organization regarding the impact of what is communicated on the decision-making process. Some responsibility is linked to corporate social responsibility (CSR), but the focus remains on the information. We propose a concept that addresses the intersection between three considered fields: emerging technologies, organizational communication and risk governance, which is the one of Responsible Organizational Communication on Emerging Technologies (ROCET) to address the responsibility of what is communicated as an ethical behavior. We aim to delve into the concept by bridging the divide between theory and practice, examining both simultaneously to garner a comprehensive understanding. This approach will help construct an understanding that meets halfway, building on knowledge accumulated from both areas. Therefore, two analyses will be conducted in parallel: a critical literature review around the “responsible communication” concept and a discourse analysis of standalone reports published by governmental bodies regarding the use of a specific emerging technology, namely artificial intelligence (AI). Using a single case analysis approach, the analysis aims to problematize one's communication regarding a public discourse while challenging such constitutions by exploring models of responsible communication. There is a gap in the literature in referring to this term as this research does. The literature focuses either on the communication conducted by organizations as part of their corporate responsibility strategy or from a communication theory perspective, concentrating on how to convey a message effectively. Alternatively, it looks at the matter from the emerging technologies perspective, where the focus is on information communication referring to the technology
APA, Harvard, Vancouver, ISO, and other styles
6

Gajos, Krzysztof, and Howard Shrobe. "Delegation, Arbitration and High-Level Service Discovery as Key Elements of a Software Infrastructure for Pervasive Computing." 2003. http://hdl.handle.net/1721.1/6721.

Full text
Abstract:
The dream of pervasive computing is slowly becoming a reality. A number of projects around the world are constantly contributing ideas and solutions that are bound to change the way we interact with our environments and with one another. An essential component of the future is a software infrastructure that is capable of supporting interactions on scales ranging from a single physical space to intercontinental collaborations. Such infrastructure must help applications adapt to very diverse environments and must protect people's privacy and respect their personal preferences. In this paper we indicate a number of limitations present in the software infrastructures proposed so far (including our previous work). We then describe the framework for building an infrastructure that satisfies the abovementioned criteria. This framework hinges on the concepts of delegation, arbitration and high-level service discovery. Components of our own implementation of such an infrastructure are presented.
APA, Harvard, Vancouver, ISO, and other styles
7

Chen, Horng-Shen, and 陳宏申. "Finding the best indicator of chemical molecular similarity to assist AI drug discovery." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/gj5g92.

Full text
Abstract:
碩士<br>國立臺灣大學<br>生物科技管理碩士在職學位學程<br>107<br>The whole process of new drug development includes the exploration and efficacy study of early drug candidates, as well as preclinical animal tests and clinical human trials for product development. After confirming the clinical efficacy and safety, the drug can then be registered for marketing. It takes an average of 10 to 15 years to develop a new drug, and at the same time has to bear the huge R&D expenditure and the risk of high failure rate. Since the development of new drugs is time consuming, shortening the time for early drug evaluation and drug screening for candidates can not only speed up the process of drug development but also reduce the total cost of research and development. The law of similarity describes that chemical molecules of similar structures share similar chemical activities. Molecular similarity refers to the degree of structural similarity between two chemical molecules. The law of similarity is one of the important theoretical foundations for drug development. Several models of molecular similarity are used during drug development to predict candidate drug activities, including pharmacokinetics, toxicology and metabolic distribution. The application of molecular similarity comparison to assist drug candidate screening can improve the success rate of preclinical drug development. However, the involvement of AI system to effectively improve this process of candidate selection has not been discussed in depth. The research of this thesis is to find a better model of chemical molecular similarity combined with artificial intelligence to assist selection of candidate drugs. It is expected that the combination of AI in the new drug exploration stage can efficiently predict and screen out drug candidates with ideal therapeutic potential, which will not only shorten the time of early stage drug development, but also accelerate the research and development process and reduce the overall research and development costs.
APA, Harvard, Vancouver, ISO, and other styles
8

LaMacchia, Brian A. "Internet Fish." 1996. http://hdl.handle.net/1721.1/6770.

Full text
Abstract:
I have invented "Internet Fish," a novel class of resource-discovery tools designed to help users extract useful information from the Internet. Internet Fish (IFish) are semi-autonomous, persistent information brokers; users deploy individual IFish to gather and refine information related to a particular topic. An IFish will initiate research, continue to discover new sources of information, and keep tabs on new developments in that topic. As part of the information-gathering process the user interacts with his IFish to find out what it has learned, answer questions it has posed, and make suggestions for guidance. Internet Fish differ from other Internet resource discovery systems in that they are persistent, personal and dynamic. As part of the information-gathering process IFish conduct extended, long-term conversations with users as they explore. They incorporate deep structural knowledge of the organization and services of the net, and are also capable of on-the-fly reconfiguration, modification and expansion. Human users may dynamically change the IFish in response to changes in the environment, or IFish may initiate such changes itself. IFish maintain internal state, including models of its own structure, behavior, information environment and its user; these models permit an IFish to perform meta-level reasoning about its own structure. To facilitate rapid assembly of particular IFish I have created the Internet Fish Construction Kit. This system provides enabling technology for the entire class of Internet Fish tools; it facilitates both creation of new IFish as well as additions of new capabilities to existing ones. The Construction Kit includes a collection of encapsulated heuristic knowledge modules that may be combined in mix-and-match fashion to create a particular IFish; interfaces to new services written with the Construction Kit may be immediately added to "live" IFish. Using the Construction Kit I have created a demonstration IFish specialized for finding World-Wide Web documents related to a given group of documents. This "Finder" IFish includes heuristics that describe how to interact with the Web in general, explain how to take advantage of various public indexes and classification schemes, and provide a method for discovering similarity relationships among documents.
APA, Harvard, Vancouver, ISO, and other styles

Books on the topic "AI in Discovery"

1

Clevert, Djork-Arné, Michael Wand, Kristína Malinovská, Jürgen Schmidhuber, and Igor V. Tetko, eds. AI in Drug Discovery. Springer Nature Switzerland, 2025. http://dx.doi.org/10.1007/978-3-031-72381-0.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Lefevre, Renato. Nel 500o dell'impresa colombiana: Dalle prime cronache ai "Cantari" di Giuliano Dati. [Fondazione Marco Besso], 1992.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
3

Mazzoli, Enrico. Dall'Adriatico ai ghiacci: Ufficiali dell'Austria-Ungheria con i loro marinai istriani, fiumani e dalmati alla conquista dell'Artico. Edizioni della Laguna, 2003.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
4

Guillet, Fabrice. Advances in Knowledge Discovery and Management: Volume 2. Springer Berlin Heidelberg, 2012.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
5

Montessori, Maria. Fa xian hai zi: Liao jie he ai hai zi de xin fang fa = the discovery of the child. Zhongguo fa zhan chu ban she, 2003.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
6

Bramer, M. A. (Max A.), 1948-, Petridis Miltos, Hopgood Adrian A, and British Computer Society. Specialist Group on Artificial Intelligence, eds. Proceedings of AI-2010, the Thirtieth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence: Incorporating applications and innovations in intelligent systems XVIII. Springer, 2011.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
7

Beardsley, Ian. An AI Discovery. lulu.com, 2017.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
8

Beardsley, Ian. A Second AI Discovery. Lulu.com, 2017.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
9

AI for Scientific Discovery. Taylor & Francis Group, 2023.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
10

AI for Scientific Discovery. Taylor & Francis Group, 2023.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "AI in Discovery"

1

Hastings, Janna. "AI for Data Interpretation." In AI for Scientific Discovery. CRC Press, 2023. http://dx.doi.org/10.1201/9781003226642-3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Hastings, Janna. "AI for Reproducible Research." In AI for Scientific Discovery. CRC Press, 2023. http://dx.doi.org/10.1201/9781003226642-4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Hastings, Janna. "Introduction." In AI for Scientific Discovery. CRC Press, 2023. http://dx.doi.org/10.1201/9781003226642-1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Hastings, Janna. "Limitations of AI and Strategies for Combating BIAS." In AI for Scientific Discovery. CRC Press, 2023. http://dx.doi.org/10.1201/9781003226642-5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Hastings, Janna. "AI for Managing Scientific Literature and Evidence." In AI for Scientific Discovery. CRC Press, 2023. http://dx.doi.org/10.1201/9781003226642-2.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Hastings, Janna. "Conclusion." In AI for Scientific Discovery. CRC Press, 2023. http://dx.doi.org/10.1201/9781003226642-6.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Corbucci, Luca, Anna Monreale, Cecilia Panigutti, Michela Natilli, Simona Smiraglio, and Dino Pedreschi. "Semantic Enrichment of Explanations of AI Models for Healthcare." In Discovery Science. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-45275-8_15.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Sanitt, Nigel. "Mathematics and AI." In Culture, Curiosity and Communication in Scientific Discovery. Routledge, 2018. http://dx.doi.org/10.4324/9780429459818-13.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Zhang, Shichao, and Chengqi Zhang. "Pattern Discovery in Probabilistic Databases." In AI 2001: Advances in Artificial Intelligence. Springer Berlin Heidelberg, 2001. http://dx.doi.org/10.1007/3-540-45656-2_53.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Bai, Qifeng, Jian Ma, and Tingyang Xu. "AI Deep Learning Generative Models for Drug Discovery." In Applications of Generative AI. Springer International Publishing, 2024. http://dx.doi.org/10.1007/978-3-031-46238-2_23.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "AI in Discovery"

1

Nursanti, Yuli Bangun, Imam Sujadi, Ira Kurniawati, Arum Nur Wulandari, and Riki Andriatna. "AI-Assisted Theorem Discovery: Revolutionizing Mathematical Exploration." In 2025 International Conference on Frontier Technologies and Solutions (ICFTS). IEEE, 2025. https://doi.org/10.1109/icfts62006.2025.11031488.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Jagannathan, J., S. Kanishka, S. Thanushree, and M. S. Bhuvaneswari. "Collaboration of AI with Project Management." In 2024 International Conference on IT Innovation and Knowledge Discovery (ITIKD). IEEE, 2025. https://doi.org/10.1109/itikd63574.2025.11004933.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Suzuki, Yasuhiro, and Kaoru Shimada. "Instance-Based Discovery of ItemSBs Leveraging Individuality Through Discretization." In 2024 International Conference on AI x Data and Knowledge Engineering (AIxDKE). IEEE, 2024. https://doi.org/10.1109/aixdke63520.2024.00024.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Liebling, Daniel J., Malcolm Kane, Madeleine Grunde-McLaughlin, Ian Lang, Subhashini Venugopalan, and Michael Brenner. "Towards AI-assisted Academic Writing." In Proceedings of the 1st Workshop on AI and Scientific Discovery: Directions and Opportunities. Association for Computational Linguistics, 2025. https://doi.org/10.18653/v1/2025.aisd-main.4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Badrus, Moch Abdulloh Salim, Ika Novita Sari, Septiana Azha, Moh Zulfikri, and Sutantri. "AI-Infused Research and Development in Universities: Accelerating Scientific Discovery." In 2024 4th International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE). IEEE, 2024. http://dx.doi.org/10.1109/icacite60783.2024.10616647.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Mahilnan, V., Ms B. Nandhini, N. Santhosh, R. MelkyAbishake, S. Ranganathan, and P. Maheshwaran. "AI-Powered Drug Discovery: Accelerating Precision Medicine with Deep Learning." In 2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES). IEEE, 2024. https://doi.org/10.1109/icses63760.2024.10910685.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Periyasamy, Madhavan. "AI-Driven Multi-Omics Integration for Enhanced Drug Discovery Pipelines." In 2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI). IEEE, 2025. https://doi.org/10.1109/icmsci62561.2025.10894291.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Navarro, Álvaro Serrano, Juan Ignacio Alvarez Arenas, Alberto Gonzalez Calatayud, Jose Antonio Enríquez, Fernando Martínez De Benito, and Fátima Sanchez Cabo. "Virtual-Cardio-Drug: Ai-Powered Sbvs for Cardiovascular Drug Discovery." In 2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS). IEEE, 2025. https://doi.org/10.1109/cbms65348.2025.00118.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Madunuri, Ram, Sai Manoj Yellepeddi, Chetan Sasidhar Ravi, Subrahmanyasarma Chitta, Venkata Sri Manoj Bonam, and Vinay Kumar Reddy Vangoor. "AI-Enhanced Drug Discovery Accelerating the Identification of Potential Therapeutic Compounds." In 2024 Asian Conference on Intelligent Technologies (ACOIT). IEEE, 2024. https://doi.org/10.1109/acoit62457.2024.10939855.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Arun, Bhingardive Akshada, and B. N. Bansode. "Visionary AI: Transforming Diabetic Retinopathy Discovery through Advanced Deep Learning Models." In 2024 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA). IEEE, 2024. https://doi.org/10.1109/iccubea61740.2024.10774872.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "AI in Discovery"

1

Varikoti, Rohith, Chathuri Jeewanthi Kombala Nanayakkara Thambiliya, Stephanie Thibert, et al. Automated AI-driven Molecular Design for Therapeutic Discovery. Office of Scientific and Technical Information (OSTI), 2024. http://dx.doi.org/10.2172/2462814.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Massey, Joe, Neil Majithia, and Elena Simperl. Generative AI tools for data discovery and use. Open Data Institute, 2024. https://doi.org/10.61557/odzd4015.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Devarakonda, Ranjeet, Jitendra Kumar, Dalton Lunga, Jong Choi, and Giri Prakash. AI-Driven Data Discovery to Improve Earth System Predictability. Office of Scientific and Technical Information (OSTI), 2021. http://dx.doi.org/10.2172/1769671.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Puglisi, Anna, and Daniel Chou. China’s Industrial Clusters: Building AI-Driven Bio-Discovery Capacity. Center for Security and Emerging Technology, 2022. http://dx.doi.org/10.51593/20220012.

Full text
Abstract:
China is banking on applying AI to biotechnology research in order to transform itself into a “biotech superpower.” In pursuit of that goal, it has emphasized bringing together different aspects of the development cycle to foster multidisciplinary research. This data brief examines the emerging trend of co-location of AI and biotechnology researchers and explores the potential impact it will have on this growing field.
APA, Harvard, Vancouver, ISO, and other styles
5

Boyce, Brad, Remi Dingreville, David Adams, et al. BeyondFingerprinting: AI-guided discovery of robust materials & processes. Office of Scientific and Technical Information (OSTI), 2024. http://dx.doi.org/10.2172/2462990.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Serbin, Shawn, Scott Giangrande, Chongai Kuang, Nathan Urban, and Line Pouchard. AI to Automate ModEx for Optimal Predictive Improvement and Scientific Discovery. Office of Scientific and Technical Information (OSTI), 2021. http://dx.doi.org/10.2172/1769662.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Pasupuleti, Murali Krishna. Mathematical Modeling for Machine Learning: Theory, Simulation, and Scientific Computing. National Education Services, 2025. https://doi.org/10.62311/nesx/rriv125.

Full text
Abstract:
Abstract Mathematical modeling serves as a fundamental framework for advancing machine learning (ML) and artificial intelligence (AI) by integrating theoretical, computational, and simulation-based approaches. This research explores how numerical optimization, differential equations, variational inference, and scientific computing contribute to the development of scalable, interpretable, and efficient AI systems. Key topics include convex and non-convex optimization, physics-informed machine learning (PIML), partial differential equation (PDE)-constrained AI, and Bayesian modeling for uncertainty quantification. By leveraging finite element methods (FEM), computational fluid dynamics (CFD), and reinforcement learning (RL), this study demonstrates how mathematical modeling enhances AI-driven scientific discovery, engineering simulations, climate modeling, and drug discovery. The findings highlight the importance of high-performance computing (HPC), parallelized ML training, and hybrid AI approaches that integrate data-driven and model-based learning for solving complex real-world problems. Keywords Mathematical modeling, machine learning, scientific computing, numerical optimization, differential equations, PDE-constrained AI, variational inference, Bayesian modeling, convex optimization, non-convex optimization, reinforcement learning, high-performance computing, hybrid AI, physics-informed machine learning, finite element methods, computational fluid dynamics, uncertainty quantification, simulation-based AI, interpretable AI, scalable AI.
APA, Harvard, Vancouver, ISO, and other styles
8

Goncalves, André, and Donald Lucas. AI Automated Discovery of New Climate Water System Knowledge from Models and Observations. Office of Scientific and Technical Information (OSTI), 2021. http://dx.doi.org/10.2172/1769658.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Daniels, Matthew, Autumn Toney, Melissa Flagg, and Charles Yang. Machine Intelligence for Scientific Discovery and Engineering Invention. Center for Security and Emerging Technology, 2021. http://dx.doi.org/10.51593/20200099.

Full text
Abstract:
The advantages of nations depend in part on their access to new inventions—and modern applications of artificial intelligence can help accelerate the creation of new inventions in the years ahead. This data brief is a first step toward understanding how modern AI and machine learning have begun accelerating growth across a wide array of science and engineering disciplines in recent years.
APA, Harvard, Vancouver, ISO, and other styles
10

Leger, Dorian. Pre-registration: Landscape Review of AI-Powered Research Tools for Literature Review and Discovery. ResearchHub Technologies, Inc., 2025. https://doi.org/10.55277/researchhub.e7ni6r9s.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'AI in Discovery' for particular source types:
Journal articles Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography