Designing Bayesian based Adaptive Resource Constrained Hardware Algorithms for Next Generation of Embedded Systems

介绍了深度学习（DL）社区的新学习方法，允许深度学习代理在相同或新的环境中适应和持续学习，以模仿类似人类的学习，如迁移学习、少量学习和持续学习。尽管有这些方法，但要在资源受限的传感平台上实现无缝和适应性强的人工智能，仍然需要解决一些限制。首先，现有解决方案的重点往往是准确性，而缺乏对其他性能指标的关注，如内存、CPU和能耗，这些对低功耗资源受限的设备至关重要。其次，目前的工作没有考虑到学习过程中的不确定性，而是侧重于对设备的推断。我们希望超越推理，在设备上进行更具挑战性的学习。本研究项目的总体目标是为资源受限的设备（如mcu（微控制器单元）和fpga）研究高效可靠的设备上学习解决方案。具体来说，该项目的目标将包括探索不同贝叶斯持续学习方法在各种传感任务中的性能，以发现存在的问题，通过解决这些问题来研究和设计新的贝叶斯持续学习ML算法，并提出基于系统的优化技术。

Novel learning approaches from deep learning (DL) community are introduced to allow DL agents to adapt and continually learn in the same or new environments to mimic human like learning such as transfer learning, few shot learning, and continual learning. Despite these approaches there are still limitations that must be addressed to enable seamless and adaptable AI on resource constrained sensing platforms. Firstly, the existing solutions focus is often dominated by accuracy and lacks attention to other performance measures such as memory, CPU, and energy consumption which is critical to low-power resource-constrained devices. Secondly, the current work does not account for the uncertainties in the learning process and focus on inference on the device. We would like to go beyond inference and take on more challenging pursuit of learning on the device. The overall goal of this research project would be to investigate efficient and reliable on-device learning solutions for resource-constrained devices such as MCUs (microcontroller units) and FPGAs. Specifically, the aims of the project would include exploring the performance of different Bayesian continual learning approaches for various sensing tasks to find existing issues, investigate and design novel ML algorithms for Bayesian continual learning by solving these issues and propose system-based optimization techniques.