SHF: Small: Fast Sign-Off of Machine Learning Systems: From Circuit-Level Modeling to Statistical System Validation

机器学习已被广泛的新兴应用所采用，包括健康监测、自动驾驶、先进制造等，然而，由于机器学习算法的精度限制以及与其硬件实现相关的电路级非理想特性，任何机器学习系统都不可能100%准确。该项目研究了一个全新的框架，用于有效验证用纳米级集成电路实现的机器学习系统。它旨在识别和综合机器学习系统可能失败的关键情况。该项目预计将启动当今复杂机器学习系统设计方法的范式转变，从而对依赖机器智能的广泛工业部门产生直接影响。此外，拟议的教育活动为学术和工业参与者创造了大量独特的培训机会，大大改善了教育基础设施，为社会培养了高素质的研究人员和从业人员。如今，验证具有高吞吐量、低功耗和复杂功能的机器学习系统是一项极具挑战性的任务。该项目通过开发一个由两个主要部分组成的新型验证框架来应对重大挑战：（1）角情况生成和（2）罕见故障率估计。提出了物理电路模型和统计生成模型来合成大量的测试用例，降低了物理记录难以观察的角点用例的实验成本。此外，一种新的配方，基于子集划分和图嵌入，开发了有效地检查可能失败的测试用例，从而估计罕见的故障率，这是昂贵的捕获随机抽样。基于这些数学工具，该项目的框架提供了一个基本的基础设施，可以促进许多机器学习应用的根本突破。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Machine learning has been adopted by a broad range of emerging applications, including health monitoring, autonomous driving, advanced manufacturing, etc. However, any machine learning system cannot be 100% accurate due to the accuracy limitation posed by machine learning algorithms and the circuit-level non-ideal features associated with its hardware implementation. This project investigates a radically new framework for efficient validation of machine learning systems implemented with nano-scale integrated circuits. It aims to identify and synthesize the critical corner cases for which a machine learning system is likely to fail. The project is expected to initialize a paradigm shift in today's design methodology for complex machine learning systems, thereby leading to an immediate impact on a broad range of industrial sectors relying on machine intelligence. In addition, the proposed education activities create a large number of unique training opportunities for both academic and industrial participants, substantially improving the education infrastructure and generate high-quality researchers and practitioners for the society. Today, validating a machine learning system with high throughout, low power and complex functionality is an extremely challenging task. This project attacks the grand challenge by developing a novel validation framework composed of two major components: (1) corner-case generation and (2) rare-failure rate estimation. Both physical circuit models and statistical generative models are proposed to synthesize a large amount of test cases, reducing the experimental cost to physically record the corner-cases that are difficult to observe. Furthermore, a novel formulation, based on subset partition and graph embedding, is developed to efficiently inspect the likely-failed test cases and consequently estimate the rare- failure rate that is expensive to capture by random sampling. Built upon these mathematical tools, the project's framework offers a fundamental infrastructure that could facilitate radical breakthroughs over numerous machine learning applications.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.