Kick-off Workshop of the Nordic Research Network in Unconventional Computing

The workshop is arranged by the Unconventional Computing Nordic Research Network, supported by NordForsk through the programme Nordic Research Networks within Natural Science and Related Engineering Fields.

The network includes researchers from:

• Örebro University, Sweden
• University of Turku, Finland
• Norwegian University of Science and Technology, Norway
• Technical University of Denmark, Denmark

Topics include, but are not limited to:

• neuromorphic computing
• brain-inspired computing
• in-materio computation
• reservoir computing
• Ising machines
• cellular automata

Practical information

• Date: 17–18 June 2026
• Venue: LAB 105, Innovasalen, Örebro University
• Format: Lunch-to-lunch workshop
• Participants: Approximately 25 invited participants
• Language: English

Invited speakers

17 June

Ayça Özçelikkale, Associate Professor, Uppsala University

Talk title: On the Structure of Neuromorphic Computation: Spikes, Memory, and Reset

Abstract

Neuromorphic computing is an emerging paradigm for low-latency, energy-efficient information processing, in which brain-inspired models such as spiking neural networks play a central role. At the same time, deep state space models have recently shown strong performance in temporal modelling. Although these approaches come from different research traditions, both implement stateful transformations of temporal input sequences. This talk presents a principled correspondence between these models through a dynamical systems approach. It also discusses broader questions about reset, stability and memory in learning, and what these may mean for the design of neuromorphic systems.

About the speaker

Ayça Özçelikkale is Associate Professor at the Department of Electrical Engineering at Uppsala University, Sweden. Before joining Uppsala University, she held a postdoctoral position at Chalmers University of Technology and visiting positions at Ericsson Research, Queen’s University and EURECOM. Her research includes signal processing, machine learning, neuromorphic computing and communications.

18 June

Claudio Gallicchio, Associate Professor, University of Pisa

Talk title: Perspectives on and Beyond Reservoir Computing

Abstract

This talk revisits reservoir computing as an alternative paradigm for sequence modelling, motivated by the well-known difficulties of training recurrent neural networks and the growing demand for efficient, hardware-compatible learning systems. After introducing the core principles of reservoir computing and its natural suitability for neuromorphic and physical implementations, the talk discusses the limitations of conventional echo state networks in terms of long-range information propagation. The second part presents recent research directions on non-dissipative reservoir dynamics and new reservoir architectures that move reservoir computing towards the deep learning regime while preserving fast training and hardware suitability.

About the speaker

Claudio Gallicchio is Associate Professor of Computer Science at the University of Pisa. His research focuses on reservoir computing, recurrent neural networks and dynamical systems for deep learning, with a particular focus on hardware-aware and energy-efficient models. He is involved in several research projects that combine ideas from deep learning and neuromorphic hardware for sustainable artificial intelligence.

Important information

The network is unable to provide financial support for travel or accommodation. Coffee breaks, lunches and the workshop dinner will be provided at no cost.

Contact

For questions about the workshop, please contact:

Denis Kleyko, Örebro University
Alberto Giaretta, Örebro University