Improving Neural Network Reliability for Dynamic System Modeling and Control Optimization Through the Use of Confidence Measures

通过使用置信度措施提高动态系统建模和控制优化的神经网络可靠性

• 批准号: 9362155
• 负责人: Yuchun Lee
• 金额: $ 5.76万
• 依托单位: Unica Technologies, Incorporated
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1994
• 资助国家: 美国
• 起止时间: 1994-03-15 至 1994-11-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9362155&HistoricalAwards=false
• 关键词: Improving; Neural; Network; Reliability; Dynamic

9362155 Lee No algorithms exist that generate comprehensive, statistically sound reliability information for neural networks. Reliability of neural nets is affected by (1) the amount of training data, (2) input novelty, (3) data consistency and (4) time-varying system dynamics. Confidence measures con gauge network reliability by indication when sufficient training data has been presented for good generalization, when a neural network's output should be trusted, and when periodic retraining should occur in slow time-varying dynamic systems. They can also help automate neural network controllers in a closed-loop environment. Confidence generation algorithms complement virtually all neural nets and can help their integration with existing controllers into production environments. Unica will develop and test confidence algorithms for each of the four independent factors affecting reliability. This research will be based on established theories and innovative ideas, using artificial and real-world data from "Alcoa's aluminum reduction process. The principal investigator, Yuchun Lee, along with neural network expert, Dr. Richard Lippmann of MIT Lincoln Laboratory, provide the perfect combination of real-world application exposure and theoretical background to conduct this research. Successful results are expected to have great commercial potential for incorporation into neural network-based process control applications. ***

小行星9362155 没有算法存在，产生全面的，统计上健全的可靠性信息的神经网络。 神经网络的可靠性受到以下因素的影响：（1）训练数据的数量，（2）输入的新奇性，（3）数据的一致性和（4）时变系统动态。 置信度通过指示何时已经提供了足够的训练数据用于良好的泛化，何时应该信任神经网络的输出，以及何时应该在慢时变动态系统中进行周期性再训练来衡量网络的可靠性。 它们还可以帮助在闭环环境中实现神经网络控制器的自动化。 置信度生成算法补充了几乎所有的神经网络，可以帮助它们与现有的控制器集成到生产环境中。Unica将为影响可靠性的四个独立因素中的每一个开发和测试置信度算法。 这项研究将基于既定的理论和创新的想法，使用人工和真实世界的数据，从“美国铝业的铝还原过程。 首席研究员李宇春沿着麻省理工学院林肯实验室的神经网络专家理查德·李普曼博士，提供了现实世界应用接触和理论背景的完美结合来进行这项研究。 成功的结果，预计将有很大的商业潜力，纳入基于神经网络的过程控制应用。 ***