Tessera
Folgen

Quality AI Labs Berlin

@qailabs.bsky.social

Lab head: @sparsity.bsky.social tu.berlin/uniml

15 Posts102 Follower225 Folgt
Stefan Haufe@sparsity.bsky.social · 7mo ago

I am happy to announce the successful PhD defense of now Dr. rer. nat. Rick Wilming at TU Berlin, which he passed with distinction (summa cum laude) with this thesis on "Explainable AI under Scrutiny: From Empirical Investigations to Analytical Insights". See: www.linkedin.com/posts/stefan...

I am happy to announce the successful PhD defense of now Dr. rer. nat. Rick Wilming at TU Berlin, which he passed with distinction (summa cum laude). In his thesis entitled "Explainable AI under...

I am happy to announce the successful PhD defense of now Dr. rer. nat. Rick Wilming at TU Berlin, which he passed with distinction (summa cum laude). In his thesis entitled "Explainable AI under Scru...

linkedin.com

Stefan Haufe@sparsity.bsky.social · 7mo ago

XAI techniques have been proposed as tools to "debug" machine learning models by revealing what they have learned. Challenging this narrative, we find that XAI attributions are strongly dominated by salient features independent of the role of these features for a model. See: tinyurl.com/48m4axnv

Explainable AI techniques have been proposed as tools to "debug" machine learning models. In a popular example, authors discovered a photographer's watermark when applying XAI in an ima...

Explainable AI techniques have been proposed as tools to "debug" machine learning models. In a popular example, authors discovered a photographer's watermark when applying XAI in an image classificat...

linkedin.com

Stefan Haufe@sparsity.bsky.social · last yr.

Very useful software not only for neuroscientists provided by @tsbinns.com . Bispectral analyses allow robust determination of transmission delays, phase-amplitude coupling and quantification of non-sinusoidality of oscillations. See also our methods preprints: lnkd.in/gSsrqYpX lnkd.in/gCaXDggK

LinkedIn

This link will take you to a page that’s not on LinkedIn

lnkd.in

Thomas S. Binns@tsbinns.com · last yr.

Happy to announce that our paper on the PyBispectra toolbox for robust analyses of cross-frequency coupling, waveshape, and communication latencies is available now in the Journal of Open Source Software! 📖 Paper: doi.org/10.21105/joss.08504 💻 Toolbox: pybispectra.readthedocs.io

Thomas S. Binns@tsbinns.com · 2y ago

Excited to have my PhD project paper exploring the network mechanisms of neuromodulation accepted for publication! We show how deep brain stimulation and medication exert a shared modulation of motor network synchrony in Parkinson's disease.

Schematic summary of therapeutic effects of dopamine and deep brain stimulation (DBS) across spatial, spectral, and temporal scales in Parkinson's disease.
Stefan Haufe@sparsity.bsky.social · 2y ago

Happy to share our perspective preprint on the state of explainable AI. XAI needs to shift from algorithm- to problem-driven development to make sure methods can serve meaningful purposes. We are looking forward to discuss, here or on alphaxiv.org/abs/2409.14590 .

Explainable AI needs formal notions of explanation correctness | alphaXiv

The use of machine learning (ML) in critical domains such as medicine poses risks and requires regulation. One requirement is that decisions of ML systems in high-risk applications should be human-und...

alphaxiv.org