CIF: Small: Learning Signal Representations for Multiple Inference Tasks

CIF：小：学习多个推理任务的信号表示

• 批准号: 1527388
• 负责人: Maxim Raginsky
• 金额: $ 50万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-08-01 至 2020-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1527388&HistoricalAwards=false
• 关键词: CIF; Small; Learning; Signal; Representations

Rapid advances in high-performance computing and widespread availability of massive datasets are bringing about a paradigm shift in the theory and practice of signal representations, geared towards inference and learning. A signal representation is a compressed summary that only retains those features of the signal that are salient for a class of inference tasks. This project provides a comprehensive theoretical and algorithmic framework for signal representations, which is sufficiently broad to cover both the traditional types of signal representations, such as vector quantization and sparse codes, and the more modern types, inspired by recent advances in machine learning and signal processing for Big Data. Under this framework, the statistical performance and the computational complexity of signal representations are addressed in a unified manner by imposing structural constraints on the encoding map, the decoding map, and the model space of the representation, while simultaneously tailoring these objects to the class of tasks of interest. This unification leads to new theoretical and algorithmic insights into highly structured internal representations that are a key factor in recent spectacular success of deep neural networks on challenging tasks in visual, audio, and speech analytics.

大量数据集的高性能计算和广泛可用性的快速进步正在使信号表示理论和实践的范式转移，这是针对推论和学习的。信号表示是一个压缩摘要，仅保留信号的那些特征，这些特征对于一类推理任务而言是显着的。该项目为信号表示形式提供了一个全面的理论和算法框架，该框架足够广泛，可以涵盖传统类型的信号表示形式（例如向量量化和稀疏代码）以及更现代的类型，灵感来自于机器学习和信号处理的最新进展。在此框架下，信号表示的统计性能和计算复杂性是通过在编码地图，解码地图和表示形式的模型空间上施加结构性约束的同时，以同时将这些对象定制到感兴趣的任务类别，以统一的方式解决了结构性约束。这种统一导致对高度结构化内部表示形式的新理论和算法见解，这是深层神经网络在视觉，音频和语音分析中挑战性任务方面取得巨大成功的关键因素。