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

arXiv:2402.18443v1 Announce Type: new
Abstract: 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. …

abstract architecture architectures article arxiv building co2 consumption cs.ai cs.lg devices discovery edge edge devices emissions expert inferencing knowledge llms network neural network novel parameters power power consumption speed type