CAREER: Scalable and Adaptable Sparsity-driven Methods for more Efficient AI Systems

人工智能（AI），特别是深度神经网络（DNN）在涉及图像、自然语言处理和蛋白质结构等许多认知任务上的准确性优于人类。不幸的是，由于高数据处理需求，人工智能系统通常运行在耗电的专用计算硬件上。量化，或逼近较小的数值，已被用于减少计算需求。然而，固定的低位宽深度神经网络可能由于量化误差而导致精度损失。许多现有的量化软件解决方案在位宽选择上也是固定的或有限的。为了解决这种权衡和利用数据稀疏性，研究团队将研究最先进的方法，并开发新的数据量化、编码和压缩算法，以与现有的人工智能系统集成。所开发的方法不仅具有提高性能的潜力，而且还具有降低功率需求和提高人工智能系统能源效率的潜力。它们将在小型设备上启用DNN推理等人工智能应用程序，从而减少云基础设施的负载，改善用户体验，提供数据隐私并避免安全风险。该项目提出的工作有可能在许多运行在储能受限设备上的人工智能应用中突破界限，例如智能传感、可穿戴设备和自动驾驶。研究和教育工具将促进和增加学生和研究界参与推进人工智能研究。这项工作将在一个为少数族裔服务的机构进行，资金将用于支持来自代表性不足群体的学生。该项目的研究目标是研究量化和压缩方法，这些方法可以利用稀疏性并提高人工智能系统的效率。首席研究员（PI）计划研究适应性量化和压缩方法，以利用人工智能系统的稀疏性，同时最大限度地减少非稀疏情况下的开销，并最大限度地减少精度损失。将研究和定义准确度、性能或能源效率的自动可调优先级之间的准确性和性能之间的权衡。PI计划开发一个可并行执行所提议方法的原型，以使所提议的方法对数据中心和高级硬件架构真正有效。所提出的方法将被打包到AI向量原语库中，该库将与几个流行的深度学习框架集成，作为概念证明，主要针对GPU和CPU系统。将为Pytorch或TensorFlow等框架开发集成API，以便与其他向量原语轻松集成。软件库将与基于网络的学习平台集成，该平台具有自动反馈和激励环境，以鼓励学生参与解决人工智能挑战。该奖项反映了美国国家科学基金会的法定使命，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。

Artificial Intelligence (AI) and, in particular, Deep Neural Networks (DNN) have achieved better than human accuracy on many cognitive tasks involving images, natural language processing, and protein structure, among others. Unfortunately, due to high data processing demands, AI systems are typically run on power-hungry specialized computing hardware. Quantization, or approximation to smaller numerical values, has been used to reduce computing requirements. However, the fixed low bit-width DNNs may suffer losses in accuracy due to quantization errors. Many existing software solutions for quantization are also fixed or limited in bit-width choices. To address this trade-off and leverage data sparsity, the research team will investigate state-of-the-art methods and develop novel data quantization, encoding, and compression algorithms to integrate with existing AI systems. The methods developed have the potential to not only improve performance but also to reduce power requirements and boost the energy efficiency of AI systems. They will enable AI applications such as DNN inference on small devices, thus reducing the load on cloud infrastructure, improving user experience, providing data privacy, and avoiding security risks. The work proposed in this project has the potential to push the boundaries in many AI applications that run on energy storage-constrained devices, such as smart sensing, wearable devices, and autonomous driving. The research and educational tools will facilitate and increase student and research community participation in advancing AI research. The work will be conducted at a minority-serving institution, and the funding will support students from underrepresented groups.The research goal of this project is to investigate quantization and compression methods that can leverage sparsity and improve efficiency in AI systems. The principal investigator (PI) plans to study adaptable quantization and compression methods to leverage sparsity in AI systems while minimizing the overhead in non-sparse situations and minimizing accuracy loss. The trade-off between accuracy and performance with the proposed methods will be studied and defined for automated tunable prioritization of either accuracy, performance, or energy efficiency. The PI plans to develop a prototype with parallel execution of the proposed methods to make the proposed methods truly effective for data centers and advanced hardware architectures. The proposed methods will be packaged into an AI vector primitives library that will be integrated with several popular Deep Learning frameworks as proof of concept, primarily targeting GPU and CPU systems. An integration API will be developed for frameworks like Pytorch or TensorFlow to allow easy integration with other vector primitives. Software libraries will be integrated with a web-based learning platform with automated feedback and a motivating environment to encourage student participation in solving AI challenges.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.