We are pleased to invite researchers, academics, and practitioners to contribute chapters to the upcoming edited book titled Multi-Task Learning in Science and Engineering.
This book will explore the intersection of Deep Learning and Multi-Task Learning (MTL), offering insights into methods, techniques, and applications across a wide range of scientific and engineering domains

The book will be structured into two volumes:

Volume I: Science – Dedicated to foundational scientific applications of MTL in fields such as biology, chemistry, physics, and mathematics. This volume will focus on MTL’s role in data-driven discovery, cross-disciplinary learning, and hypothesis generation within scientific research.

Volume II: Engineering – Focused on the use of MTL in engineering and practical real-world applications, including biomedicine, robotics, automation, and materials design. This volume will emphasize MTL’s impact on optimization, industry-specific adaptations, and performance efficiency.

Deadlines:

31 January 2025: Submission of intention to contribute, specifying the volume (Science or Engineering), the topic(s), and a tentative title of your chapter

1 May 2025: Full chapter submission

1 July 2025: Feedback on submitted chapters

1 September 2025: Final version submission


Each chapter should be between 20 and 40 pages, including figures and references. Original research, review articles, and case studies are all welcome.

Submissions should be emailed to multitasklearning.book@gmail.com and should include the following editors' email addresses in CC:
pardalos@ufl.edu , panos.pardalos@gmail.com , giuseppe.nicosia@unict.it , giuseppe.nicosia.1@gmail.com , giulio.giaquinta@studium.unict.it , giulio.giaquinta7@gmail.com

Editors:

Panos Pardalos, University of Florida, USA
Giuseppe Nicosia, University of Catania, Italy
Giulio Giaquinta, University of Catania, Italy