项目名称: 先进储备池神经计算方法及其在时间模式识别中的应用
项目编号: No.61201406
项目类型: 青年科学基金项目
立项/批准年度: 2013
项目学科: 电子学与信息系统
项目作者: 宋青松
作者单位: 长安大学
项目金额: 24万元
中文摘要: 时间模式识别是视频跟踪、语音识别等智能系统的关键共性问题之一,要求算法具备时序建模能力。储备池神经网络是一类新型递归神经网络(RNN),采用"储备池"+"读取器"网络结构组织,促使棘手的RNN训练问题转化为一个简单的线性回归或分类问题。现有研究表明,储备池神经计算方法可为时间模式识别问题提供有竞争力的方案,但在泛化性能、问题适应性等方面还存在大量的理论与实际问题亟待解决。综上,本项目面向时间模式识别问题,以一类自动语音识别问题为例,结合结构风险最小化原理方法,开展储备池神经网络泛化能力研究;结合参数自适应与优化技术,开展储备池适应性研究。最终将建立一种自适应的结构风险最小化储备池算法,并实现一个车载自动语音识别原型系统,实际验证算法的有效性与先进性。本项目的成功实施有助于神经网络理论与应用研究发展,并为求解实际的时间模式识别问题提供新的思路与方法。
中文关键词: 神经计算;模式识别;受限波尔兹曼机;突变检测;目标跟踪
英文摘要: Temporal pattern recognition is one of the key and common issues for intelligent systems such as video tracking, speech recognition, which require the algorithms should be with temporal order modeling capability. Reservoir computing (RC) is a novel kind of recurrent neural network (RNN) method. It explores the separate "reservoir" and "readout" architecture, and makes the difficult RNN training problem an easy linear regression or classification problem. It has been demonstrated that RC can provide competitive solutions to temporal pattern recognition. However, there are still lots of theoretical and practical issues on the RC requiring to be further improved, such as generalization, adaptation. Therefore, concentrating on the temporal pattern recognition problems, and taking one kind of automatic speech recognition problems for example, this project studies RC generalization performance based on the structural risk minimization principle, and also studies the adaptation issue based on parameter self-adaptation and optimization techniques. Finally, this project will propose a kind of adaptive and structural-risk-minimization compatible algorithms, and also realize an automatic in-vehicle speech recognition prototype system. The validity and superiority of the proposed algorithms are approved by the system. The s
英文关键词: Neurocomputing;Pattern recognition;Restricted Boltzmann Machine;Abrupt change detection;Object tracking