# Artificial Intelligence in the Low-Level Realm -- A Survey

arXiv: https://arxiv.org/abs/2111.00881 · HTML: https://mlsanity.com/paper/2111.00881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 19 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [The Case for Learned Index Structures](https://mlsanity.com/paper/1712.01208/) (2017)
- [Training Deep Neural Networks with 8-bit Floating Point Numbers](https://mlsanity.com/paper/1812.08011/) (2018)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [ALEX: An Updatable Adaptive Learned Index](https://mlsanity.com/paper/1905.08898/) (2019)
- [Learning Memory Access Patterns](https://mlsanity.com/paper/1803.02329/) (2018)
- [RLCache: Automated Cache Management Using Reinforcement Learning](https://mlsanity.com/paper/1909.13839/) (2019)
- [Realizing Uncertainty-Aware Timing Stack in Embedded Operating System](https://mlsanity.com/paper/1802.00922/) (2018)

## Abstract (arXiv)

Resource-aware machine learning has been a trending topic in recent years, focusing on making ML computational aspects more exploitable by the edge devices in the Internet of Things. This paper attempts to review a conceptually and practically related area concentrated on efforts and challenges for applying ML in the operating systems' main tasks in a low-resource environment. Artificial Intelligence has been integrated into the operating system with applications such as voice or image recognition. However, this integration is only in user space. Here, we seek methods and efforts that exploit AI approaches, specifically machine learning, in the OSes' primary responsibilities. We provide the improvements that ML can bring to OS to make them more trustworthy. In other words, the main question to be answered is how AI has played/can play a role directly in improving the traditional OS kernel main tasks. Also, the challenges and limitations in the way of this combination are provided.