Hyperdimensional Neural Computation for Real-Time Cognitive Learning

用于实时认知学习的超维神经计算

• 批准号: 2127780
• 负责人: Mohsen Imani
• 金额: $ 30万
• 依托单位: University of California-Irvine
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-15 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2127780&HistoricalAwards=false
• 关键词: Hyperdimensional; Neural; Computation; Real; Time

With each passing year, the volume of analyzable data continues to explode, with new information gathered from a variety of video, sensors, and informatics platforms. Therefore, we face increasing needs for machine learning techniques to adaptively analyze this large-scale data and transform that into actionable knowledge. Today's machine learning algorithms, however, have the following key technical challenges: (1) they are extremely slow and inefficient on lightweight embedded devices, e.g., smartphones or smartwatches, (2) they are very vulnerable to noise and failures that often exist in highly scaled technology and network, and (3) they lack brain-like cognitive support and adaptation to provide a high quality of learning and a reason for each prediction and decision. To achieve real-time performance with high energy efficiency and robustness, we redesign algorithms using strategies that more closely model the human brain. We leverage Hyper-Dimensional Computing (HDC), a brain-inspired method, motivated by the observation that the human brain operates on high-dimensional space. In HDC, objects are encoded into high-dimensional vectors to represent neural patterns with thousands of elements. This encoding transforms data into knowledge that enables lightweight cognitive learning. In this project, we develop an infrastructure that supports a wide range of learning and cognitive tasks with high robustness and efficiency. Our open-source infrastructure provides real-time and dynamic learning, with a wide range of applications in intelligent healthcare, environmental monitoring, and smart distributed systems. The project will also support underrepresented minority students through synergistic outreach plans and educational activities, including programs for K-12 students, undergraduate research opportunities, and new course development.The novel research approaches introduced in this project aim to lay the foundations for deeper integration of brain-inspired mathematics, learning algorithm, and hardware. This includes the development of: (1) encoding methods that map various spatial-temporal data into high-dimensional space, including simple numerical values to complex video/images, (2) algorithmic solutions that enable brain-like learning and cognitive tasks over encoded data, and (3) hardware-software libraries that significantly accelerate the HDC algorithms. Our programmable processor natively supports HDC operations while utilizing extensive parallelism offered by multiple hardware platforms. We will evaluate the effectiveness of our framework on multiple large-scale systems, including smart home and environmental monitoring. Our prototypes will be fully released under an established open-source library for wide public dissemination.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.

随着时间的推移，可分析数据的数量持续爆炸式增长，从各种视频、传感器和信息平台收集到新的信息。因此，我们越来越需要机器学习技术来自适应地分析这些大规模数据并将其转化为可操作的知识。然而，今天的机器学习算法面临以下关键技术挑战：(1)它们在轻量级嵌入式设备上非常缓慢和低效，例如智能手机或智能手表；(2)它们非常容易受到高度规模化技术和网络中经常存在的噪音和故障的影响；(3)它们缺乏类似大脑的认知支持和适应，无法提供高质量的学习和每个预测和决策的原因。为了实现具有高能效和鲁棒性的实时性能，我们重新设计了使用更接近人类大脑模型的策略的算法。我们利用了超维计算（HDC），这是一种以大脑为灵感的方法，其动机是观察到人类大脑在高维空间上运行。在HDC中，对象被编码为高维向量，以表示具有数千个元素的神经模式。这种编码将数据转换为知识，从而实现轻量级的认知学习。在这个项目中，我们开发了一个基础设施，它支持广泛的学习和认知任务，具有高鲁棒性和效率。我们的开源基础设施提供实时和动态学习，在智能医疗保健、环境监测和智能分布式系统中具有广泛的应用。该项目还将通过协同推广计划和教育活动，包括K-12学生项目、本科生研究机会和新课程开发，支持代表性不足的少数民族学生。本项目引入的新颖研究方法旨在为大脑启发数学、学习算法和硬件的更深层次整合奠定基础。这包括：(1)将各种时空数据映射到高维空间的编码方法，包括简单的数值到复杂的视频/图像，(2)在编码数据上实现类脑学习和认知任务的算法解决方案，以及(3)显著加速HDC算法的硬件-软件库。我们的可编程处理器原生支持HDC操作，同时利用多个硬件平台提供的广泛并行性。我们将评估我们的框架在多个大型系统上的有效性，包括智能家居和环境监测。我们的原型将在一个已建立的开源库下全面发布，以供广泛的公众传播。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。

项目成果

Brain-Inspired Hyperdimensional Computing for Ultra-Efficient Edge AI

用于超高效边缘人工智能的类脑超维计算

• DOI: 10.1109/codes-isss55005.2022.00017
• 发表时间: 2022
• 期刊: 2022 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS
• 作者: Amrouch, Hussam;Imani, Mohsen;Jiao, Xun;Aloimonos, Yiannis;Fermuller, Cornelia;Yuan, Dehao;Ma, Dongning;Barkam, Hamza E.;Genssler, Paul R.;Sutor, Peter
• 通讯作者: Sutor, Peter

Bayesian Optimization for Expensive Smooth-Varying Functions

• DOI: 10.1109/mis.2022.3163227
• 发表时间: 2022-07
• 期刊: IEEE Intelligent Systems
• 影响因子: 6.4
• 作者: Mahdi Imani;M. Imani;Seyede Fatemeh Ghoreishi

Adaptive neural recovery for highly robust brain-like representation

• DOI: 10.1145/3489517.3530659
• 发表时间: 2022-07
• 期刊: Proceedings of the 59th ACM/IEEE Design Automation Conference
• 作者: Prathyush P. Poduval;Yang Ni;Yeseong Kim;K. Ni;Raghavan Kumar;Rosario Cammarota;M. Imani

HyDREA: Utilizing Hyperdimensional Computing For A More Robust and Efficient Machine Learning System

HyDREA：利用超维计算打造更强大、更高效的机器学习系统

• DOI: 10.1145/3524067
• 发表时间: 2022
• 期刊: ACM Transactions on Embedded Computing Systems
• 影响因子: 2
• 作者: Morris, Justin;Ergun, Kazim;Khaleghi, Behnam;Imani, Mohsen;Aksanli, Baris;Rosing, Tajana
• 通讯作者: Rosing, Tajana

Stochastic Computing for Reliable Memristive In-Memory Computation

• DOI: 10.1145/3583781.3590307
• 发表时间: 2023-06
• 期刊: Proceedings of the Great Lakes Symposium on VLSI 2023
• 作者: Mohsen Riahi Alam;M. Najafi;N. Taherinejad;M. Imani;Lu Peng