arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.18443cs.LGcs.AI
收藏

LeMo-NADe:使用 LLM 进行多参数神经架构发现

LeMo-NADe: Multi-Parameter Neural Architecture Discovery with LLMs

University of Maine(缅因大学)

Md Hafizur Rahman, Prabuddha Chakraborty

AI总结:

提出 LeMo-NADe 框架,结合专家系统与 LLM,依据用户指定的功耗、模型大小、推理速度和 CO2 排放等多参数自动发现边缘设备神经网络架构。

摘要:

构建高效的神经网络架构可能是一项耗时的任务,需要大量专业知识。对于边缘设备而言,这一任务尤其具有挑战性,因为必须考虑推理过程中的功耗、模型大小、推理速度以及 CO2 排放等参数。本文中,我们提出一种新颖框架,旨在根据用户定义的参数、专家系统以及在大量开放领域知识上训练的 LLM,自动发现新的神经网络架构。所提出的框架(LeMo-NADe)专为非 AI 专家使用而设计,不需要预先确定的神经架构搜索空间,并考虑大量边缘设备特有的参数。我们使用 CIFAR-10、CIFAR-100 和 ImageNet16-120 数据集,并以 GPT-4 Turbo 和 Gemini 作为 LLM 组件,实现并验证了这一神经架构发现框架。我们观察到,所提出框架能够快速(数小时内)发现复杂的神经网络模型,这些模型在用户定义的多种应用设置中表现极其出色。

英文摘要:

Building efficient neural network architectures can be a time-consuming task requiring extensive expert knowledge. This task becomes particularly challenging for edge devices because one has to consider parameters such as power consumption during inferencing, model size, inferencing speed, and CO2 emissions. In this article, we introduce a novel framework designed to automatically discover new neural network architectures based on user-defined parameters, an expert system, and an LLM trained on a large amount of open-domain knowledge. The introduced framework (LeMo-NADe) is tailored to be used by non-AI experts, does not require a predetermined neural architecture search space, and considers a large set of edge device-specific parameters. We implement and validate this proposed neural architecture discovery framework using CIFAR-10, CIFAR-100, and ImageNet16-120 datasets while using GPT-4 Turbo and Gemini as the LLM component. We observe that the proposed framework can rapidly (within hours) discover intricate neural network models that perform extremely well across a diverse set of application settings defined by the user.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑