Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems

• URL: http://arxiv.org/abs/2104.04000v1
• Date: Thu, 8 Apr 2021 18:29:30 GMT
• Title: Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems
• Authors: Cong Hao, Deming Chen
• Abstract summary: autonomous systems essentially require multi-modal multi-task (MMMT) learning. We first discuss the opportunities of applying MMMT techniques in autonomous systems and then discuss the unique challenges that must be solved. We formulate the MMMT model and heterogeneous hardware implementation co-design as a differentiable optimization problem.
• Score: 7.3473356077331475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optimizing the quality of result (QoR) and the quality of service (QoS) of AI-empowered autonomous systems simultaneously is very challenging. First, there are multiple input sources, e.g., multi-modal data from different sensors, requiring diverse data preprocessing, sensor fusion, and feature aggregation. Second, there are multiple tasks that require various AI models to run simultaneously, e.g., perception, localization, and control. Third, the computing and control system is heterogeneous, composed of hardware components with varied features, such as embedded CPUs, GPUs, FPGAs, and dedicated accelerators. Therefore, autonomous systems essentially require multi-modal multi-task (MMMT) learning which must be aware of hardware performance and implementation strategies. While MMMT learning has been attracting intensive research interests, its applications in autonomous systems are still underexplored. In this paper, we first discuss the opportunities of applying MMMT techniques in autonomous systems and then discuss the unique challenges that must be solved. In addition, we discuss the necessity and opportunities of MMMT model and hardware co-design, which is critical for autonomous systems especially with power/resource-limited or heterogeneous platforms. We formulate the MMMT model and heterogeneous hardware implementation co-design as a differentiable optimization problem, with the objective of improving the solution quality and reducing the overall power consumption and critical path latency. We advocate for further explorations of MMMT in autonomous systems and software/hardware co-design solutions.

Related papers

• Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities [59.02391344178202]
  Vision foundation models (VFMs) serve as potent building blocks for a wide range of AI applications. The scarcity of comprehensive training data, the need for multi-sensor integration, and the diverse task-specific architectures pose significant obstacles to the development of VFMs. This paper delves into the critical challenge of forging VFMs tailored specifically for autonomous driving, while also outlining future directions.
  arXiv  Detail & Related papers  (2024-01-16T01:57:24Z)
• Machine Learning Insides OptVerse AI Solver: Design Principles and Applications [74.67495900436728]
  We present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI solver. We showcase our methods for generating complex SAT and MILP instances utilizing generative models that mirror multifaceted structures of real-world problem. We detail the incorporation of state-of-the-art parameter tuning algorithms which markedly elevate solver performance.
  arXiv  Detail & Related papers  (2024-01-11T15:02:15Z)
• MultiIoT: Benchmarking Machine Learning for the Internet of Things [70.74131118309967]
  The next generation of machine learning systems must be adept at perceiving and interacting with the physical world. sensory data from motion, thermal, geolocation, depth, wireless signals, video, and audio are increasingly used to model the states of physical environments. Existing efforts are often specialized to a single sensory modality or prediction task. This paper proposes MultiIoT, the most expansive and unified IoT benchmark to date, encompassing over 1.15 million samples from 12 modalities and 8 real-world tasks.
  arXiv  Detail & Related papers  (2023-11-10T18:13:08Z)
• Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices [0.4915744683251151]
  We propose a framework for the joint optimization of unimodal backbones and multimodal fusion networks with hardware awareness on resource-constrained devices. Harmonic-NAS achieves 10.9% accuracy improvement, 1.91x latency reduction, and 2.14x energy efficiency gain.
  arXiv  Detail & Related papers  (2023-09-12T21:37:26Z)
• ALT: An Automatic System for Long Tail Scenario Modeling [15.76033166478158]
  We present an automatic system named ALT to deal with this problem. Several efforts are taken to improve the algorithms used in our system, such as employing various automatic machine learning related techniques. To build the system, many optimizations are performed from a systematic perspective, and essential modules are armed.
  arXiv  Detail & Related papers  (2023-05-19T02:35:39Z)
• M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design [95.41238363769892]
  Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. Current MTL regimes have to activate nearly the entire model even to just execute a single task. We present a model-accelerator co-design framework to enable efficient on-device MTL.
  arXiv  Detail & Related papers  (2022-10-26T15:40:24Z)
• H2H: Heterogeneous Model to Heterogeneous System Mapping with Computation and Communication Awareness [16.244832640402496]
  We propose a novel mapping algorithm with both computation and communication awareness. By slightly trading computation for communication, the system overall latency and energy consumption can be largely reduced. The superior performance of our work is evaluated based on MAESTRO modeling.
  arXiv  Detail & Related papers  (2022-04-29T02:26:18Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Tackling Variabilities in Autonomous Driving [15.374442918002813]
  We propose a novel heterogeneous multi-core AI accelerator (HMAI) to provide the hardware substrate for the driving automation tasks with variability. We also propose a deep reinforcement learning (RL)-based task scheduling mechanism FlexAI, to resolve task mapping issue.
  arXiv  Detail & Related papers  (2021-04-21T08:51:40Z)
• AutonoML: Towards an Integrated Framework for Autonomous Machine Learning [9.356870107137095]
  Review seeks to motivate a more expansive perspective on what constitutes an automated/autonomous ML system. In doing so, we survey developments in the following research areas. We develop a conceptual framework throughout the review, augmented by each topic, to illustrate one possible way of fusing high-level mechanisms into an autonomous ML system.
  arXiv  Detail & Related papers  (2020-12-23T11:01:10Z)
• Distributed and Democratized Learning: Philosophy and Research Challenges [80.39805582015133]
  We propose a novel design philosophy called democratized learning (Dem-AI) Inspired by the societal groups of humans, the specialized groups of learning agents in the proposed Dem-AI system are self-organized in a hierarchical structure to collectively perform learning tasks more efficiently. We present a reference design as a guideline to realize future Dem-AI systems, inspired by various interdisciplinary fields.
  arXiv  Detail & Related papers  (2020-03-18T08:45:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.