Leveraging the manifold hypothesis for learning representations in deep neural networks

利用流形假设学习深度神经网络中的表示

• 批准号: 341366-2013
• 负责人: Vincent, Pascal
• 金额: $ 1.82万
• 依托单位: Université de Montréal
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2014
• 资助国家: 加拿大
• 起止时间: 2014-01-01 至 2015-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=549325
• 关键词: Leveraging; manifold; hypothesis; learning; representations

Automating intelligent decision taking is easy once starting from the right, high-level representation of relevant information. But sensory input, whether biological (e.g. information relayed by eye and optic nerve, or ear) or electronic (e.g. digital camera or sound recording) start from a very large low-level representation (e.g. millions of pixel intensities) where any potentially relevant information for decision making is hidden, awfully diffuse and scrambled. A fundamental challenge is thus to develop approaches that are able to discover and exploit the hidden statistical regularities in data to learn to produce useful higher level representations from low level ones. In this research program I will leverage a geometric characterization of such statistical regularities in order to develop novel techniques able to extract meaningful representations. Significant progress on this objective could constitute a breakthrough in elucidating one of the key mechanisms of intelligence. It will translate into better artificial perception (vision, audition) systems, lift artificial intelligence capabilities closer to human capabilities, and take to the next level the fundamental science and capabilities of algorithm that underly many modern technological successes such as the Google search engine, the Siri intelligent personal agent, or the self-driving car.

一旦从相关信息的正确、高级表示开始，自动化智能决策就变得很容易。但感觉输入，无论是生物输入（例如，通过眼睛和视神经或耳朵传递的信息）还是电子输入（例如数码相机或录音），都是从非常大的低级表示（例如数百万像素强度）开始的，其中任何与决策相关的潜在相关信息都被隐藏、极其分散和混乱。因此，一个根本的挑战是开发能够发现和利用数据中隐藏的统计规律的方法，以学习从低级表示生成有用的高级表示。在这个研究项目中，我将利用这种统计规律的几何特征来开发能够提取有意义的表示的新技术。这一目标的重大进展可能会成为阐明情报关键机制之一的突破。它将转化为更好的人工感知（视觉、听觉）系统，使人工智能能力更接近人类能力，并将谷歌搜索引擎、Siri智能个人代理或自动驾驶汽车等许多现代技术成功的基础科学和算法能力提升到一个新的水平。