Autonomous Intelligent Machines & Systems

简要描述研究背景，包括潜在影响：人工智能（AI）为加速药物发现、材料科学、气候科学和医学科学等领域的科学发现提供了许多机会。人工智能与传统科学方法的合作将是至关重要的，因为传统方法通常需要大量的时间和资源，限制了创新的步伐。为了解决各种科学挑战并实现科学发现，必须开发新的人工智能方法。人们通常不能简单地将标准的ML技术应用于科学问题，因为它需要领域知识和对数据的理解，因此必须开发创新的方法。这项工作的潜在影响包括降低实验成本，缩短发现生命周期，促进科学和工业应用的变革性进步。目标和目标：我的主要目标是开发尖端的人工智能方法，推动科学发现。我目前正在研究的一个例子与分子设计有关，我的研究旨在改善新分子结构的产生，加速药物设计和材料创造等领域的进展。本研究有几个关键目标：开发新的人工智能模型，能够提出具有特定期望特性的创新分子结构；将开发的方法应用于药物发现和材料科学的实际用例；研究方法的新颖性：本研究将重点关注科学挑战和开发新的人工智能方法来解决这些问题。这种新颖性将通过探索先进的人工智能方法和提出新的替代方法，通过探索基本的数学和科学思想来实现。在分子设计方面，我们正在开发一种创新的方法，将生成模型与优化技术相结合。这种一般性的方法将有助于人工智能在科学领域的理论理解和实际应用。与EPSRC的战略和研究领域（项目涉及的EPSRC研究领域）保持一致：本研究与EPSRC的几个关键战略重点保持一致，特别是在人工智能、计算和理论化学以及数学科学领域。它支持EPSRC更广泛的目标，即促进计算方法的创新，并将其应用于解决现实世界的科学问题。该项目有助于化学发现的计算方法的进步，促进医疗技术和数字经济的突破，并与EPSRC对使用人工智能解决科学和工程领域跨学科挑战的关注保持一致。任何涉及的公司或合作者：除了我的两位主管Stephen Robertsand ye - whye Teh，目前的合作者包括Leo Klarner和Tim Rudner

Brief description of the context of the research including potential impact: ArtificialIntelligence (AI) offers many opportunities for accelerating scientific discovery in fields like drugdiscovery, materials science, climate science, and medical sciences. The use of AI in collaborationwith traditional scientific methods will be crucial as traditional methods often require significanttime and resources, limiting the pace of innovation. In order to solve various scientific challengesand enable scientific discovery, novel AI methods must be developed. One often cannot simply applystandard ML techniques to scientific problems, as it requires domain knowledge and understandingof the data, so innovative methods must be developed. The potential impact of this work includes reducing experimental costs, shortening the discovery lifecycle, and fostering transformative advancesin scientific and industrial applications.Aims and Objectives: My primary aim is to develop cutting-edge AI methodologies that driveforward scientific discovery. One example of this that I am currently working on relates to moleculardesign, where my research aims to improve the generation of new molecular structures, acceleratingprogress in areas such as drug design and material creation. This research has a few key objectives:Develop novel AI models capable of proposing innovative molecular structures with particular desired propertiesApply the developed methods to practical use cases in drug discovery and materials scienceNovelty of the research methodology: This research will focus on scientific challenges andthe development of novel AI methods to solve them. This novelty will come through exploring advanced AI methods and proposing new alternative methodologies, through exploring fundamentalmathematical and scientific ideas. In the case of molecular design, we are developing an innovativeapproach by combining generative models with optimization techniques. This general approach willcontribute to both the theoretical understanding and practical application of AI in scientific fields.Alignment to EPSRC's strategies and research areas (which EPSRC research area theproject relates to): This research aligns with several of the EPSRC's key strategic priorities,particularly in the areas of Artificial Intelligence, Computational and Theoretical Chemistry, andMathematical Sciences. It supports EPSRC's broader goals of fostering innovation in computationalmethodologies and applying them to solve real-world scientific problems. The project contributesto the advancement of computational methods for chemical discovery, promoting breakthroughs inHealthcare Technologies and Digital Economy, as well as aligning with the EPSRC's focus on theuse of AI for solving interdisciplinary challenges in science and engineering.Any companies or collaborators involved: In addition to my two supervisors, Stephen Robertsand Yee-Whye Teh, current collaborators include Leo Klarner and Tim Rudner