The pervasive diffusion of Cyber Physical Systems (CPSs) profoundly changed the way to interact with the surrounding environment. Usually equipped with sensors and actuators that provide context awareness and action capabilities, in the recent period, we are witnessing an evolution of these systems towards a new level of intelligence. Through the Artificial Intelligence (AI), we are able to build a novel type of systems known as Intelligent Cyber Physical Systems (ICPSs), where a cognition layer is involved to enable a “reasoning” step after the computation. In such a context, Deep Learning can be considered a powerful tool to address complex tasks, however it typically requires models with a large number of parameters and extensive training datasets, making it unsuitable for Edge pervasive applications where resources are limited, and real-time processing is crucial.
In light of these limitations, neuromorphic computing has emerged as a promising alternative representing a novel paradigm within the realm of neural computation, offering a unique approach to modeling and understanding the intricacies of the brain information processing. Born to bridge the gap between neuroscience and artificial intelligence, neuromorphic computing exploits the principles at the base of neuro-biological systems in order to process data more efficiently than traditional architectures, addressing the challenges typically encountered when working with Artificial Neural Networks (ANNs) in terms of energy efficiency, event-driven computation, and adaption to environment changes, thus making them suitable for a wide range of application domains. This workshop aims to explore the pervasive use of neuromorphic computing systems for the implementation of novel biological-inspired architectures and applications by leveraging innovative approaches and optimizing the computational resources. In this sense, we believe that the topics as well as the challenges posed by this novel paradigm are strictly related with the pervasive computing and could rise the interest of the PerCom research community, thanks also to its wide range of application fields.

The workshop aims to attract researchers from different sectors to come up with new ideas and propose discussions about solutions involving the pervasive use of the neuromorphic computing on several application domains.

The topics of interest include, but are not limited to:

• Neuromorphic algorithms and architectures;
• Neuromorphic devices;
• Bio-inspired models;
• Bio-inspired learning algorithms;
• On-device training and inference;
• Pervasive neuromorphic systems;
• Energy efficient algorithms;
• Implementation case studies;
• Neuromorphic applications;
• Spiking Neural Networks;
• Bio-inspired Deep Neural Networks.

Submission Guidelines:

 

Paper submissions should be no longer than 6 pages with a font size of 10 pt, 2-column format using the IEEE conference template (https://www.ieee.org/conferences/publishing/templates.html). Papers must be submitted electronically as PDF files. All submitted papers will be subject to single blind peer reviews by Technical Program Committee members and other experts in the field. All presented papers in the conference will be published in the proceedings of the conference and submitted to the IEEE Xplore Digital Library. Authors are requested to first register their submissions and submit their manuscripts in PDF format via EasyChair (https://easychair.org/my/conference?conf=percom2025), during the process please make sure to select “Workshop on Pervasive Neuromorphic Computing Systems and Applications“. Note that at least one author of each accepted paper must register and attend the workshop to present the paper. Failure to present the paper at the workshop will result in the withdrawal of the paper from the Proceedings.

 

Important Dates (tentative):

Paper submission deadline: December 1st, 2024

Paper notification: January 8th, 2025

Camera Ready Deadline: February 2nd, 2025