Realising the promise of neural networks for practical optimisation: improving their efficiency and effectivess through chaotic dynamics and hardware implementation

实现神经网络对实际优化的承诺：通过混沌动力学和硬件实现提高其效率和效果

• 批准号: ARC : DP0208976
• 负责人: Kate Smith-Miles
• 金额: $ 23.5万
• 依托单位: Monash University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2002
• 资助国家: 澳大利亚
• 起止时间: 2002-01-01 至 2005-12-31
• 项目状态: 已结题
• 来源: https://researchdata.edu.au/realising-promise-neural-hardware-implementation/74569
• 关键词: Realising; promise; neural; networks; practical

Realising the promise of neural networks for practical optimisation: improving their efficiency and effectivess through chaotic dynamics and hardware implementation. Combinatorial optimisation problems such as transportation routing and assembly-line scheduling are critical to the efficiency of many industries, but their combinatorial explosion makes rapid solution difficult. Neural networks (NNs) hold much potential for rapid solution though hardware implementation, but we need to improve the quality of their solutions before developing hardware. We have previously shown that the rich dynamics of chaos can improve the efficiency and effectiveness of NNs. We aim to develop new chaotic NN models, rigorously evaluate them on industrially significant problems such as those arising in manufacturing, logistics and telecommunications, and demonstrate their speed through hardware acceleration.

实现神经网络实践优化的希望：通过混乱的动力和硬件实现提高其效率和有效性。组合优化问题，例如运输路由和组装线计划对许多行业的效​​率至关重要，但是它们的组合爆炸使得快速解决方案变得困难。通过硬件实施，神经网络（NNS）具有快速解决方案的潜力，但是我们需要在开发硬件之前提高其解决方案的质量。我们以前已经表明，混乱的丰富动态可以提高NNS的效率和有效性。我们旨在开发新的混乱NN模型，并严格评估它们在工业上具有重要意义的问题，例如在制造，物流和电信中引起的问题，并通过硬件加速来证明它们的速度。