TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications

The Internet of Things (IoT) is rapidly expanding, with billions of devices collecting data about their environments. While these devices are becoming more intelligent through Machine Learning (ML), their limited resources pose a challenge for complex Deep Learning (DL) models. Sending all data to the cloud for processing can lead to delays, privacy concerns, and increased communication costs. Tiny Machine Learning (TinyML) offers a solution by enabling the local processing of data and the inference of ML models directly on resource-constrained devices like microcontrollers. This paper reviews the current state of TinyML, analyzing the types of ML models used, datasets, and device characteristics to identify development needs and future directions.

Careers

The research highlights the growing importance of TinyML in applications like smart cities, smart environments, and smart homes, driven by the increasing number of connected IoT devices. The ability to perform local inference on these devices opens up new possibilities for intelligent decision-making at the edge.

• IoT Device Developer
• Machine Learning Engineer (Edge Computing)
• Embedded Systems Engineer
• AI Researcher

Frequently asked questions

What career paths can I pursue after completing the TinyML PhD programme?

Graduates can pursue roles such as IoT Device Developer, Machine Learning Engineer specializing in Edge Computing, Embedded Systems Engineer, and AI Researcher. The programme prepares students for careers leveraging intelligent decision-making at the edge in applications like smart cities and smart homes.

What is the focus of the TinyML PhD programme?

The programme focuses on enabling inference of Deep Learning models on ultra-low-power IoT edge devices for AI applications. It addresses challenges related to processing complex ML models on resource-constrained devices, exploring solutions like local data processing and on-device model inference.

What kind of content is covered in the TinyML PhD programme?

The programme involves analyzing existing TinyML studies, examining the types of Machine Learning models used, the datasets involved, and the characteristics of devices in the field. It delves into the current state and future directions of Tiny Machine Learning technology.