Towards Evolvable and Sustainable Multimodal Machine Learning

迈向可进化和可持续的多模式机器学习

• 批准号: DE240100105
• 负责人: Dr Yadan Luo
• 金额: $ 31.77万
• 依托单位: The University of Queensland
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-07-01 至 2027-06-30
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE240100105
• 关键词: Towards; Evolvable; Sustainable; Multimodal; Machine

Machine learning is commonly limited to a single operational modality. To enable image, sound and language comprehension simultaneously would require machines to reuse knowledge and understand concepts from multimodal data. The project aims to build a sparse model and present a set of innovative algorithms to enhance model generalisation for addressing distributional and semantic shifts and minimise the computational and labelling costs for training multimodal systems. Its outcomes will enable evolvable learning of models to suit varying testing scenarios after deployment and whilst reducing energy consumption and carbon emission. The application of these techniques could benefit sectors such as E-commerce, agriculture and transport.

机器学习通常仅限于单一操作方式。要同时启用图像，声音和语言理解，将需要机器重复使用知识并从多模式数据中理解概念。该项目旨在建立一个稀疏的模型，并提出一系列创新算法，以增强模型的概括，以解决分布和语义转移，并最大程度地减少培训多模式系统的计算和标签成本。它的结果将使模型的可发展学习能够适合部署后的不同测试方案，并减少能耗和碳排放。这些技术的应用可能使电子商务，农业和运输等领域受益。