EAGER: Toward Scalable Life-long Representation Learning

EAGER：迈向可扩展的终身表征学习

• 批准号: 1247414
• 负责人: Honglak Lee
• 金额: $ 11.5万
• 依托单位: Regents of the University of Michigan - Ann Arbor
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-08-01 至 2014-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1247414&HistoricalAwards=false
• 关键词: EAGER; Toward; Scalable; Life; long

Machine learning is a powerful tool for artificial intelligence and data mining problems. However, its success critically relies on a good feature representation of the data; therefore, the problem of feature construction poses a fundamental challenge. In recent years, representation learning has emerged as a promising method for learning useful feature representations from data. However, the current state-of-the-art methods are still limited in building intelligent agents that can learn and interact with complex environments and large amounts of sensory input. Specifically, the majority of the existing methods cannot scale well to large-scale data.The goal of this project is to fill this gap by formulating a new framework that can effectively learn representations from complex environments and scale to large data. Specifically, we propose novel approaches for learning robust representations from large-scale data by (1) controlling the complexity of the feature representations and (2) adaptively modeling relevant patterns in the presence of significant amounts of irrelevant patterns or noise.Key intellectual contributions of this project will be (1) a novel framework of representation learning that provides robust representations from large amounts of unlabeled data and relatively small amounts of labeled data, and (2) theoretical and algorithmic advances for inference, learning, and related optimization problems in representation learning for large-scale, complex sensory information processing.This work will serve as a catalyst leading to applications, such as multimedia processing and search, medical image processing, speech recognition, and autonomous navigation. The results will be disseminated through publications and free software.

机器学习是解决人工智能和数据挖掘问题的有力工具。然而，它的成功关键依赖于良好的数据特征表示，因此，特征构建问题是一个根本性的挑战。近年来，表征学习已成为一种从数据中学习有用特征表征的有前途的方法。然而，目前最先进的方法仍然局限于构建能够与复杂环境和大量感觉输入学习和交互的智能代理。具体来说，现有的大多数方法不能很好地扩展到大规模数据，本项目的目标是通过制定一个新的框架来填补这一空白，该框架可以有效地从复杂环境中学习表示法，并可以扩展到大数据。具体地说，我们提出了一种从大规模数据中学习稳健表征的新方法，方法是：(1)控制特征表征的复杂性，(2)在存在大量无关模式或噪声的情况下自适应地建模相关模式。本项目的关键智力贡献将是(1)新的表征学习框架，它从大量未标记数据和相对少量的已标记数据提供稳健表征；(2)在大规模、复杂的感官信息处理的表征学习中的推理、学习和相关优化问题的理论和算法方面的进展。这项工作将成为通向应用的催化剂，例如多媒体处理和搜索，医学图像处理、语音识别和自主导航。结果将通过出版物和免费软件传播。