A Discrete-event-based Simulator for Deep Learning at Edge

• URL: http://arxiv.org/abs/2112.00952v1
• Date: Thu, 2 Dec 2021 03:13:53 GMT
• Title: A Discrete-event-based Simulator for Deep Learning at Edge
• Authors: Xiaoyan Liu, Zhiwei Xu, Yana Qin, Jie Tian
• Abstract summary: We propose a discrete-event-based edge learning simulator. It includes a deep learning module and a network simulation module. Our framework is generic and can be used in various deep learning problems before the deep learning model is deployed.
• Score: 7.096287095663305
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Novel smart environments, such as smart home, smart city, and intelligent transportation, are driving increasing interest in deploying deep neural networks (DNN) at edge devices. Unfortunately, deploying DNN on resource-constrained edge devices poses a huge challenge. If a simulator can interact with deep learning frameworks, it can facilitate researches on deep learning at edge. The existing simulation frameworks, such as Matlab, NS-3, etc., haven't been extended to support simulations of edge learning. To support large-scale training simulations on edge nodes, we propose a discrete-event-based edge learning simulator. It includes a deep learning module and a network simulation module. Specifically, it enable simulations as an environment for deep learning. Our framework is generic and can be used in various deep learning problems before the deep learning model is deployed. In this paper, we give the design and implementation details of the discrete-event-based learning simulator and present an illustrative use case of the proposed simulator.

Related papers

• Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks [93.38375271826202]
  We present a method to improve generalization and robustness to distribution shifts in sim-to-real visual quadrotor navigation tasks. We first build a simulator by integrating Gaussian splatting with quadrotor flight dynamics, and then, train robust navigation policies using Liquid neural networks. In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
  arXiv  Detail & Related papers  (2024-06-21T13:48:37Z)
• Learning rigid-body simulators over implicit shapes for large-scale scenes and vision [11.815473102158368]
  We present SDF-Sim, the first learned rigid-body simulator designed for scale. We use learned signed-distance functions (SDFs) to represent the object shapes and to speed up distance computation. For the first time in literature, we demonstrate that we can scale the GNN-based simulators to scenes with hundreds of objects and up to 1.1 million nodes.
  arXiv  Detail & Related papers  (2024-05-22T22:32:04Z)
• KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants [3.724713116252253]
  An effective instruction-following assistant can be developed by creating a simulator that can generate useful interaction data. Previous user simulators generally lacked diversity, were mostly closed domain, and necessitated rigid schema. We introduce Kaucus, a Knowledge-Augmented User Simulator framework, to outline a process of creating diverse user simulators.
  arXiv  Detail & Related papers  (2024-01-29T06:57:02Z)
• Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research [76.93956925360638]
  Waymax is a new data-driven simulator for autonomous driving in multi-agent scenes. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training. We benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions.
  arXiv  Detail & Related papers  (2023-10-12T20:49:15Z)
• Learning Interactive Real-World Simulators [96.5991333400566]
  We explore the possibility of learning a universal simulator of real-world interaction through generative modeling. We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies. Video captioning models can benefit from training with simulated experience, opening up even wider applications.
  arXiv  Detail & Related papers  (2023-10-09T19:42:22Z)
• Navigating to Objects in the Real World [76.1517654037993]
  We present a large-scale empirical study of semantic visual navigation methods comparing methods from classical, modular, and end-to-end learning approaches. We find that modular learning works well in the real world, attaining a 90% success rate. In contrast, end-to-end learning does not, dropping from 77% simulation to 23% real-world success rate due to a large image domain gap between simulation and reality.
  arXiv  Detail & Related papers  (2022-12-02T01:10:47Z)
• Continual learning autoencoder training for a particle-in-cell simulation via streaming [52.77024349608834]
  upcoming exascale era will provide a new generation of physics simulations with high resolution. These simulations will have a high resolution, which will impact the training of machine learning models since storing a high amount of simulation data on disk is nearly impossible. This work presents an approach that trains a neural network concurrently to a running simulation without data on a disk.
  arXiv  Detail & Related papers  (2022-11-09T09:55:14Z)
• Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation [98.51313127382937]
  We focus on the use of labels in the synthetic domain alone. Our approach introduces both a way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data.
  arXiv  Detail & Related papers  (2021-11-15T18:37:43Z)
• Sim-to-Real Transfer in Multi-agent Reinforcement Networking for Federated Edge Computing [11.3251009653699]
  Federated Learning (FL) over wireless multi-hop edge computing networks is a cost-effective distributed on-device deep learning paradigm. This paper presents FedEdge simulator, a high-fidelity Linux-based simulator, which enables fast prototyping, sim-to-real code, and knowledge transfer for multi-hop FL systems.
  arXiv  Detail & Related papers  (2021-10-18T00:21:07Z)
• An Active Learning Framework for Constructing High-fidelity Mobility Maps [0.0]
  We introduce an active learning paradigm that substantially reduces the number of simulations needed to train a machine learning classifier without sacrificing accuracy. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling.
  arXiv  Detail & Related papers  (2020-03-07T04:50:58Z)

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.