Title: Toward Neuro-Inspired AI: Online Data Selection, Modular Networks, and Stream-Based Continual Learning

Speaker: Constantine Dovrolis

Time and place: June 16, 12:30-13:30, Simula Research Laboratory, Kristian Augusts gate 23, room Nordmarka.

How can we design learning systems that resemble the brain—able to adapt continually, learn from streams, and generalize without a flood of labeled data?

This talk explores recent advances in sparse and modular neural networks that push machine learning in that direction. By selecting only the most informative experiences from a stream, enforcing sparsity to balance stability and plasticity, and leveraging modular structure to reduce interference and improve efficiency, we can move toward models that learn more like animals and humans. The focus is not on scaling up to larger black boxes, but on rethinking how learning itself happens under constraints. The result is a neuro-inspired agenda for machine learning that emphasizes adaptability, efficiency, and robustness in open-ended environments.

Bio: Dr. Constantine Dovrolis is the Director of the center for Computational Science and Technology (CaSToRC) at the Cyprus Institute. He will be the XM Chair in AI professor at the University of Cyprus, starting in September 2026. He is a graduate of the University of Wisconsin-Madison (Ph.D. 2000). Together with his collaborators and students, they have published in a wide range of scientific disciplines, including climate science, biology, and neuroscience.

More recently, his group has been focusing on neuro-inspired architectures for AI based on what is currently known about the structure and function of brain networks. According to Google Scholar, his publications have received about 16,000 citations with an h-index of 60. His research has been sponsored by US agencies such as NSF, NIH, DOE, DARPA, and by companies such as Google, Microsoft and Cisco. He has coordinated several multidisciplinary research projects during his 20 years tenure at Georgia Tech (USA). At the Cyprus Institute, he has formed a machine learning group of about 15 researchers, engineers and PhD students, and he is currently managing about €4M of European and national funding in the broader area of AI research and applications.