Generative Modelling and Representation Learning
Generative Modelling and Representation Learning
批准号:
2420772
负责人:
金额:
$0.0万
依托单位:
依托单位国家:
英国
项目类别:
Studentship
财政年份:
2020
资助国家:
英国
项目状态:
未结题
起止时间:
2020 至 --
中文摘要
在现代世界,原始数据是丰富的。创建能够理解这种大量信息流的模型对许多任务都非常有帮助。不幸的是,大多数数据并没有被整齐地打包成传统机器学习方法可以使用的格式。我们希望拥有能够从任何格式的数据中提取有用信息的方法。满足这一标准的学习范例是生成建模。生成模型从某个来源查看示例数据,并学习合成看起来像原始真实数据的新假数据。合成假示例本身可能对许多应用程序没有用处。然而,创建实际示例的能力所固有的是对数据的结构和形式的深刻理解。因此,在这些生成模型中,必须存在数据的“表示”,这些“表示”总结了数据的相关方面,例如数据的结构和形式。这些表示对人类和进一步的模型都很有用。生成模型可以产生对人类来说可解释的表示,为我们提供大量数据的自动和广泛的摘要,而不仅仅是平均值和方差等简单的度量。与此同时,进一步的模型可以直接在数据的表示上进行训练,而不是在原始数据本身上。由于表示包含关于原始生成模型学习的数据的浓缩信息,因此通常情况下,在表示上训练的模型需要更少的总体数据才能达到与直接在原始数据上训练的模型相同的性能水平。该项目旨在改进现有的生成建模技术,并制定新的方法从学习的生成模型中提取表征。研究界经常提出生成模型的新方法,但我们对从数据中学习到什么以及如何提取这些信息的理解往往滞后。该项目将处理非常新颖的生成建模方法,旨在加快我们对其内部工作原理的理解。这将通过结合对最先进模型的实证调查以及描述其行为的理论工作来实现。该项目属于EPSRC人工智能和机器人研究领域。目前计划在牛津大学统计学系内部进行合作。
英文摘要
Raw data is abundant in the modern world. Creating models that can make sense of this large flow of information would be very helpful for many tasks. Unfortunately, most data is not neatly packaged in a format that traditional machine learning methods can use. It is desirable to have methods that can extract useful information from data in any format. A learning paradigm that meets this criteria is generative modelling. Generative models look at example data from a certain source and learn to synthesize new fake data that looks like the original real data. Synthesizing fake examples may not be useful for many applications in and of itself. However, inherent in the ability to create realistic examples is a deep understand of the structure and form of the data. Therefore, within these generative models there must exist 'representations' of the data that summarize pertinent aspects of the data such as its structure and form. These representations are useful for both humans and further models. The generative models can be coaxed into producing representations that are interpretable to humans providing us with automatic and extensive summaries of large amounts of data that go beyond simple metrics such as the mean and variance. Parallel to this, further models can be trained directly on the representations of the data instead of on the raw data itself. Since the representations contain condensed information about the data learnt by the original generative model, it is usually the case that models trained on representations require much less overall data to achieve the same level of performance as a model trained on the raw data directly.This project aims to improve upon existing generative modelling techniques as well as formulate new ways to extract representations from learnt generative models. New methods for generative modelling are regularly proposed in the research community but our understanding of exactly what is being learnt from the data and how to extract this information often lags behind. The project will deal with very novel methods for generative modelling and aims to bring our understanding of their inner workings up to speed. This will be achieved through a combination of empirical investigation into state of the art models as well as theoretical work to characterise their behaviours.This project falls within the EPSRC Artifical Intelligence and Robotics research area.Collaboration is currently planned within the Oxford University Department of Statistics internally.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
国内基金
海外基金
Improving modelling of compact binary evolution.
-
批准号:10903001
-
项目类别:青年科学基金项目
-
资助金额:20.0万元
-
批准年份:2009
-
负责人:史蒂芬
-
依托单位: