EMEA 2023 Call for Presentations
Submit your abstract here.
The tinyML EMEA Innovation Forum is accelerating the adoption of tiny machine learning across the region by connecting the efforts of the private sector with those of academia in pushing the boundaries of machine learning and artificial intelligence on ultra-low powered devices
We welcome presentations and posters from both academia and industry in the EMEA region, that showcase new and innovative techniques and solutions in the space.
The scope of interest of the tinyML EMEA Innovation Forum 2023 includes, but is not limited to:
- 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.
- Research Track
Targets researchers in academia and industry that want to showcase research progress and results, especially contributions from Ph.D. students. The track will feature posters that present research topics of interest that include, but are not limited to:
- tinyML Datasets: Public release of new datasets to tinyML; frameworks that automate dataset development; survey and analysis of existing tiny datasets that can be used for research
- tinyML Applications: Novel applications across all fields and emerging use cases; discussions about real-world use cases; user behavior and system-user interaction; survey on practical experiences
- tinyML Algorithms: Federated learning or stream-based active learning methods; deep learning and traditional machine learning algorithms; pruning, quantization, optimization methods; security and privacy implications
- tinyML Systems: Profiling tools for measuring and characterizing performance and power; solutions that involve hardware and software co-design; characterization of tiny real-world embedded systems; in-sensor processing, design, and implementation
- tinyML Software: Interpreters and code generator frameworks for tiny systems; optimizations for efficient execution; software memory optimizations; neural architecture search methods
- tinyML Hardware: Power management, reliability, security, performance; circuit and architecture design; ultra-low-power memory system design; MCU and accelerator architecture design and evaluation
- tinyML Evaluation: Measurement tools and techniques; benchmark creation, assessment and validation; evaluation and measurement of real production systems
Format: This year’s tinyML EMEA Innovation Forum will feature a mixture of invited luminaries in the field and a selection of presentations from this call. The abstract should be a 1-2 page PDF and a Word document including the title, authors, affiliations, e-mail address of the contact author, as well as a schematic summary of the content of the presentation.
Submit your abstract here.
Rosina Haberl firstname.lastname@example.org
- Alessandro Grande (Edge Impulse, Italy) – Chair
- Hajar Mousanif (Cadi Ayyad University, Morroco) – Vice-chair
- Abstract due Feb 28, 2023
- Author notification March 10, 2023