Francesco Martinuzzi

Postdoctoral researcher | Chaos and ML | @mpi_pks

[Francesco Martinuzzi @MartinuzziFra]

What is the minimally effective way to construct a reservoir computer that can learn chaotic dynamics?

In my new paper, I demonstrate that deterministically constructed reservoirs with minimal topologies (MESNs) consistently outperform conventional random-initialized ESNs.

1/2

[Nonlinear Sciences Papers @SciencePapers]

Storage and selection of multiple chaotic attractors in minimal reservoir computers

Francesco Martinuzzi, Holger Kantz
https://t.co/KcyFZNmUce [𝚗𝚕𝚒𝚗.𝙲𝙳 𝚌𝚜.𝙻𝙶]

[Francesco Martinuzzi @MartinuzziFra]

Why it matters:

- More reliable than random-initialized models
- Lower tuning overhead, less trial and error
- Stronger stability across runs

📄 Read more: https://t.co/p6waQBYwTF

2/2

[Francesco Martinuzzi @MartinuzziFra]

What is the minimally effective way to construct a reservoir computer that can learn chaotic dynamics?

In my new paper, I demonstrate that deterministically constructed reservoirs with minimal topologies (MESNs) consistently outperform conventional random-initialized ESNs.

1/2

[DurstewitzLab @DurstewitzLab]

Can time series #FoundationModels like Chronos zero-shot generalize to unseen #DynamicalSystems (DS)?

No, they cannot.

But *DynaMix* can, the first FM based on principles of DS reconstruction, capturing the long-term evolution of out-of-domain DS: https://t.co/fL1CLATTpB

(1/6)

[Dr. Chris Rackauckas @ChrisRackauckas]

New blog post: How chaotic is chaos? How some AI for Science / SciML papers are overstating accuracy claims.

https://t.co/SQvbZ3T8C8

#julialang #sciml #chaos #ergodic #ai4science

[ScaDS.AI Dresden/Leipzig @Sca_DS]

⭕️ This week @Sca_DS.
Our scientists (and their green colleagues🍃) are moving up. In recent years, @Sca_DS has grown rapidly. With the additional space on the 5th floor, our center in Leipzig has now more than doubled in size. This week the move was mostly completed. #RoomToGrow

[ISP • Image and Signal Processing @isp_uv_es]

🚨 New paper out in @NatureComms

We review how #AI is transforming modeling & understanding extreme weather & climate events like floods, heatwaves, and wildfires📷

🔗Read it! https://t.co/WJWw93wROf

[Environmental Data Science @EnvDataScience]

New article:

Earth System Data Cubes: Avenues for advancing Earth system research

👉 https://t.co/pMtdt2YNEC

@dmlmont, @MiguelDMahecha, @gdkrmr, @ancapopescu7, @felixcremer, @ChaonanJi, @TejaKattenborn, @MFerrer_Laura, @MartinuzziFra, @m_soechting, @khalilteber #AI #datacubes

[Claudio Gallicchio @claudiogallicc1]

🚀 Call for Papers 🚀
Special Session: Reservoir Computing in the Deep Learning Era: Theory, Models, Applications, and Hardware
📍 IJCNN 2025 | 30 June - 5 July 2025 | Rome, Italy
🔗 https://t.co/KQwLoyMLoz
📅 Submission Deadline: January 30, 2025 (extended)

[Ruben Ohana @oharub]

Generating cat videos is nice, but what if you could tackle real scientific problems with the same methods? 🧪🌌
Introducing The Well: 16 datasets (15TB) for Machine Learning, from astrophysics to fluid dynamics and biology.
🐙: https://t.co/PMAHK7i2lG
📜: https://t.co/6XLJA5lJnI

[ScaDS.AI Dresden/Leipzig @Sca_DS]

🌳On Wednesday, the 3rd annual Topic Area Meeting of the Earth and Environmental Sciences @ScaDS_AI took place. With great success!
🌍Throughout the day, more than 30 participants discussed their research across environmental sensor types, scales and ML architectures. #AppliedAI

[Francesco Martinuzzi @MartinuzziFra]

@felix_m_koehler You can do it much faster without backprop

https://t.co/xX2PStqiEI

[Francesco Martinuzzi @MartinuzziFra]

This isn't the actual Lorenz attractor: it's a prediction made by Echo State Networks after being trained for only ~1 second. To know more about the work done in the first #GSoC month with #JuliaLang and #SciML head over to https://t.co/su1RuKtOX2

[Daniel Klotz @ido87]

Hey there 👋

Want to do a Phd with me? Apply: https://t.co/da5Wb0yagW

[Miguel Mahecha @MiguelDMahecha]

To get 2 reviewers per paper at @EnvDataScience, I have to invite >20. Meanwhile, I get daily review requests I have to decline—already committed to project and tenure reviews + journal duties. So I can't blame anyone, but how do we fix this unsustainable system??? #PeerReview

[Stefano Nichele @stenichele]

🔥New paper🔥

A sensitivity analysis of cellular automata and heterogeneous topology networks: partially-local CA and homogeneous homogeneous random boolean networks

https://t.co/HmajcJsUB0

Led by @TomEivindGlover , w/ @Stormjotne, @MartinuzziFra, P. Lind & me

@hiofnorge

[EarthSystemDynamics @EGU_ESD]

New #EGUhighlights: Cautionary remarks on the planetary boundary visualisation https://t.co/h3Z86P0dJw

[Stefano Nichele @stenichele]

🔥New preprint🔥

"A Sensitivity Analysis of Cellular Automata and Heterogeneous Topology Networks: Partially-Local CA and Homogeneous Homogeneous RBNs"

https://t.co/jTPuuEqHho

led by @TomEivindGlover, with @Stormjotne, @MartinuzziFra, P. Lind and myself

[Francesco Martinuzzi @MartinuzziFra]

@crosslabstokyo thanks, that's nice to know! I'll be following updates on this!

[David Montero Loaiza @dmlmont]

And another day with a great workshop on #AwesomeSpectralIndices here in Tartu 🇪🇪 #FOSS4GE2024! 🥳 Thank you very much to all participants for the nice time and the insightful discussion! @MartinuzziFra @Rsc4Earth @idiv @UniLeipzig @GoogleDevEurope