3/5 More specifically, we demonstrate that modifying the SO model learning parameters gives rise to four different regimes that can account for both creative products and inconclusive outcomes, thus providing a framework for studying and understanding the creative potential of learning systems.

2/5 Developed to model complex adaptive systems in ALife and advocated as a candidate for minimal agency, the Self-Optimization (SO) model can be considered as the 3rd operational mode of the classical Hopfield Network, leveraging the power of associative memory to enhance optimization performance.

1/5 Now in Artificial Life: our research on the creativity of unsupervised learning! Core finding: a simple model of attractor networks with Hebbian learning is sufficient to constitute a (minimal) creative process, yielding creative products as solutions of the optimization. doi.org/10.1162/ARTL...

4/4 Locally, we're part of a rich AI research ecosystem, including the Finnish Center of AI (FCAI), Helsinki Institute for Information Technology (HIIT) @icthiit.bsky.social and the Finnish @ellis.eu institute, a world-class research hub in AI and machine learning.

1/5 🌟 Our latest peer-reviewed research bridges psychology and AI/reinforcement learning (RL)! We explore how AI models of intrinsic motivation can formalise the "need for competence" in Self-Determination Theory (SDT), a very popular theory of human motivation. Preprint: arxiv.org/abs/2502.07423.

2/3 We compared two drawing robots, a mechanical plotter and an anthropomorphized arm, creating the same still-life drawings. Surprisingly, differences in robot embodiment did not affect creativity ratings. But seeing the art being made, and what makes it, boosted how creative people perceived them.

1/3 Out now: new paper on people's perception of AI (robot) creativity! Core finding: we attribute more creativity to a creative act if people not only see the final artwork, but also its creation process & the robot making it. Video: vimeo.com/1073134853 Open-access paper: doi.org/10.1145/3711...

(1/3) This week at #neurips2024: our work on "Diversity Progress” (DP) to improve unsupervised skill learning. Meet authors Erik Lintunen & Nadia Ady at the Intrinsically Motivated Open-ended Learning (IMOL) workshop: Sun 15th, 8:15+, West Meeting Room 217–219. Paper: openreview.net/forum?id=nz9...

I’m in Melbourne, visiting @jon-mcc.bsky.social at Sensilab / @monashuniversity.bsky.social (+ escaping Finnish winter!). I’ll be around for 2 more weeks-> email if you fancy a chat! A super fresh overview talk, covering 6 recent projects on #creativity #AI #HCI: sensilab.monash.edu/forums/three...

Hello back! :) I gave my mental health a break from social media and made time for my wonderful daughter, who has added an entire new dimension to my experience of life, which I'm so grateful for. Expect me to be rather quiet, and post mostly about fresh research, conferences and jobs.