Consolidating TinyML lifecycle with large language models: Reality, illusion, or opportunity?

This talk discusses the feasibility of leveraging Large Language Models (LLMs) to automate and streamline the TinyML lifecycle. We developed a prototype framework that utilizes the natural language understanding and code generation capabilities of LLMs to automate the deployment process for TinyML applications. In our case study, which involves a simple fruit classification project on an Arduino Nano 33 BLE board, we evaluate the effectiveness of this approach.