Quadratic Observable Operator Models for efficient prediction and classification of stochastic time series

用于有效预测和分类随机时间序列的二次可观察算子模型

• 批准号: 15397344
• 负责人: Professor Dr. Herbert Jaeger
• 金额: --
• 依托单位: Faculty of Science and Engineering
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2005
• 资助国家: 德国
• 起止时间: 2004-12-31 至 2009-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/15397344?language=en
• 关键词: Quadratic; Observable; Operator; Models; efficient

Hidden Markov Models (HMMs) are the core modelling method in speech recognition systems and are increasingly employed in biosequence analysis. Their main drawbacks are slow learning algorithms and suboptimal models due to the local optimization character of known learning algorithms. Observable operator models (OOMs) are a recently developed alternative to HMMs whose associated, novel learning algorithm needs only a fraction of learning time, yields more accurate models, and is asymptotically correct (finds the global optimimum). One drawback of OOMs that has prevented their widespread use so far is that they may predict negative values for probabilities. The proposed project investigated quadratic and norm-OOMs, in which non-negativity of predicted probabilities is guaranteed by design. In the first two years of funding (the project is now in month 19/24) the basic mathematical theory of quadratic and norm-OOMs was established and learning algorithms (of an altogether novel kind) were developed and tested on synthetic datasets; all meeting and surpassing the originally envisioned goals.

隐马尔可夫模型是语音识别系统中的核心建模方法，并且越来越多地用于生物序列分析。它们的主要缺点是学习算法速度慢，由于已知的学习算法的局部最优特性，次优模型。可观测算子模型（OOM）是最近开发的替代HALTH的一种方法，其相关的新颖的学习算法只需要一小部分学习时间，产生更准确的模型，并且是渐近正确的（找到全局最优值）。迄今为止，OOM的一个阻碍其广泛使用的缺点是它们可能预测概率的负值。该项目研究了二次和范数OOM，其中预测概率的非负性是由设计保证的。在资助的前两年（该项目现在是19/24月），建立了二次和范数OOM的基本数学理论，并开发了学习算法（一种全新的），并在合成数据集上进行了测试;所有这些都达到并超过了最初设想的目标。