TinyNS: Platform-aware Neurosymbolic Auto Tiny Machine Learning
TinyNS: Platform-aware Neurosymbolic Auto Tiny Machine Learning
复制标题
DOI：
10.1145/3603171
复制
发表时间：
2024-05-01
影响因子：
2
通讯作者：
Srivastava，Mani
中科院分区：
文献类型：
--
作者：
Saha，Swapnil Sayan;Sandha，Sandeep Singh;Srivastava，Mani
处于极端边缘的机器学习已经实现了大量智能、时间关键型和远程应用。然而，在有限的平台资源约束下，部署能够执行高级符号推理并满足底层系统规则和物理的可解释人工智能系统是具有挑战性的。在本文中，我们介绍了第一个平台感知的神经符号架构搜索框架TinyNS，用于联合优化符号和神经运算符。TinyNS提供配方和解析器来自动编写五种神经符号模型的微控制器代码，将符号技术的上下文感知和完整性与机器学习模型的健壮性和性能相结合。TinyNS在不连续、条件、数值和分类搜索空间上使用快速、无梯度的黑盒贝叶斯优化器，在硬件资源预算内找到符号代码和神经网络的最佳协同。为了保证可部署性，在优化过程中，TinyNStalks会指向目标硬件。通过几个案例研究，我们通过部署微控制器级别的神经符号模型来展示TinyNSS的实用性。在所有用例中，TinyNSo都优于纯神经或纯符号方法，同时保证在真实硬件上执行。
Machine learning at the extreme edge has enabled a plethora of intelligent, time-critical, and remote applications. However, deploying interpretable artificial intelligence systems that can perform high-level symbolic reasoning and satisfy the underlying system rules and physics within the tight platform resource constraints is challenging. In this article, we introduceTinyNS, the first platform-aware neurosymbolic architecture search framework for joint optimization of symbolic and neural operators.TinyNSprovides recipes and parsers to automatically write microcontroller code for five types of neurosymbolic models, combining the context awareness and integrity of symbolic techniques with the robustness and performance of machine learning models.TinyNSuses a fast, gradient-free, black-box Bayesian optimizer over discontinuous, conditional, numeric, and categorical search spaces to find the best synergy of symbolic code and neural networks within the hardware resource budget. To guarantee deployability,TinyNStalks to the target hardware during the optimization process. We showcase the utility ofTinyNSby deploying microcontroller-class neurosymbolic models through several case studies. In all use cases,TinyNSoutperforms purely neural or purely symbolic approaches while guaranteeing execution on real hardware.