Call for Papers:

Special Issue on “tinyML”

Abstract or Paper Registration Deadline
April 13, 2023
Final Submission Deadline
April 13, 2023

tinyML integrates and cultivates the rapidly expanding subfield of ultra-low power machine learning technologies and methods dealing with machine intelligence at the cloud’s edge. These integrated “small” machine learning applications necessitate “full-stack” (hardware, system, software, and applications) solutions that include machine learning architectures, techniques, tools, and methodologies capable of executing on-device analytics. Multiple sensing modalities (vision, audio, motion, environmental, human health monitoring, etc.) are used with extreme energy efficiency, often in the sub-milliwatt range, to enable machine intelligence at the physical-digital interface. We envision a future with billions of distributed intelligent devices powered by energy-efficient machine-learning technologies that sense, evaluate, and act independently to create a more sustainable environment for everyone!

This special issue intends to highlight the present state of the art in tinyML, including cross-layer design and verification methodologies, datasets and frameworks, algorithms, applications, and systems, as well as their interdependencies in the design of future tinyML systems.

This special issue of IEEE Micro will feature outstanding, peer-reviewed publications on this emerging topic with interest in nurturing the community.

This special session solicits 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