About

PROGRAM PREVIEW:

• TinyML in the Real World

This track will cover the latest advancements in small-scale machine learning and their real-world applications, examining the opportunities and challenges of developing such solutions and addressing societal issues and Sustainable Development Goals (SDGs) through them. It will also explore the shift from traditional Digital Signal Processing (DSP) to deep learning-based techniques to handle the increasing complexity and volume of data generated by various devices and sensors.

• Algorithms and Optimization Techniques

This track will focus on recent innovations to bring highly efficient inference models to real devices by optimizing performance and energy on-device using techniques such as optimized network architectures and compression techniques. The track will also delve into emerging approaches to benchmarking performance on tiny devices.

• MLOps, development and deployment tools

This track will cover the crucial tools for enabling tinyML technology, including recent advancements in software for developing, optimizing and deploying tinyML solutions. It will also discuss data collection, pre-processing, and curation as an important step before the development phase, and best practices, methodologies, and tools to facilitate the whole process and make tinyML solutions ubiquitous in our lives.

• Hardware and Sensors

This track will focus on innovation and advancements within the tinyML hardware and sensor ecosystem, highlighting emerging trends that will shape the future of tinyML solutions. It will delve into the tinyML hardware and sensor ecosystem, showcasing current market-ready solutions as well as what’s on the horizon, exploring novel architectures like NPUs, custom hardware acceleration, and neuromorphic technology. The track will also cover new sensor paradigms and architectures and provide a comprehensive overview of the state of the art in tinyML hardware.