Tiny Machine Learning

Special Session on Tiny Machine Learning - June 30 2025 - July 5 2025, Rome, Italy

About this Special Session

We are glad to announce the Special Session on Tiny Machine Learning, to be held in Rome, Italy in IJCNN 2025. All the information about the conference can be found at the official website.

The computing everywhere paradigm is paving the way for the pervasive diffusion of tiny devices (such as Internet-of-things or edge computing devices) endowed with intelligent abilities. Achieving this goal requires machine and deep learning solutions to be completely redesigned to fit the severe technological constraints on computation, memory, and power consumption typically characterizing these tiny devices. This is exactly where Tiny Machine Learning (TinyML) comes into play. TinyML is a new and promising area of Machine Learning aimed at designing and developing Machine and Deep Learning solutions that can be executed on tiny devices.

This special session aims at exploring the latest advancements, models, algorithms, methodologies, and applications in TinyML.

IJCNN Logo

Call for papers

Authors are invited to submit articles combining aspects of tiny devices and ML.

We welcome papers on a wide range of topics, including but not limited to:

  • Optimization and compression methods for TinyML models and algorithms
  • Effective and efficient TinyML models and algorithms for resource-constrained devices
  • Energy-efficient strategies and mechanisms for TinyML
  • Hardware platforms for TinyML: microcontroller, neural/hardware accelerators, reconfigurable hardware
  • Data collection and preprocessing for TinyML
  • Benchmarks, datasets and performance evaluation for TinyML
  • Security and privacy in TinyML
  • On-device TinyML: models, algorithms and mechanisms
  • TinyML for concept drift and adaptation of TinyML models
  • Semi-supervised and incremental learning for TinyML
  • Ethics and regulatory issues in TinyML
  • Natural Learning Processing in TinyML
  • Distributed and Federated Learning and Inference
  • Fault detection and diagnosis in TinyML
  • Human-Machine Interactions in TinyML
  • Sustainability of TinyML
  • Applications of TinyML (Smart Cities, Healthcare, Networking, Industry 4.0/5.0, etc..)

Important dates

Submission rules and form can be found in the official conference website.

  • Submission deadline: 15th January 2025
  • Notification of acceptance: 31th March 2025
  • Conference date: 30th June 2025 - 5th July 2025

Organizers

  • Manuel Roveri - Politecnico di Milano, Italy
  • Marco Zennaro - The Abdus Salam International Centre for Theoretical Physics (ICTP), Trieste, Italy
  • Brian Plancher - Barnard College, Columbia University, USA
  • Eiman Kanjo - Imperial College London, UK

For further information, you can contact the publicity commitee members at massimo.pavan@polimi.it and hazemhesham.shalby@polimi.it



Program committee members

Coming soon.