Recent searches

No recent searches

Search options

Only available when logged in.
mstdn.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A general-purpose Mastodon server with a 500 character limit. All languages are welcome.

Administered by:

Server stats:

11K
active users

mstdn.social: AboutStatusProfiles directoryPrivacy policyTerms of service

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#MachineLearning

71 posts63 participants13 posts today
Jorge Miguel Silva

📢 Just published our new work on federated random forests for privacy-preserving machine learning!
📄 “A Federated Random Forest Solution for Secure Distributed Machine Learning”
📌 IEEE: doi.org/10.1109/CBMS65348.2025

📂 Supplementary slides:
🔗 doi.org/10.5281/zenodo.16539345

We're advancing secure AI without sharing data. Feedback & collaborations welcome! 🚀
#FederatedLearning #PrivacyPreservingAI #MachineLearning #OpenScience #IEEE #DataScience #Zenodo #ResearchSoftware #Reproducibility

SRF IRIS

What does it actually mean when we say that generative AI raises ethical questions?
🔵 Dr. Thilo Hagendorff, our research group leader at IRIS3D, has taken this question seriously and systematically. With his interactive Ethics Tree, he has created one of the most comprehensive overviews of ethical problem areas in generative AI: lnkd.in/ebzZYaU7
More than 300 clearly defined issues – ranging from discrimination and disinformation to ecological impacts – demonstrate the depth and scope of the ethical landscape. This “tree” does not merely highlight risks, but structures a field that is increasingly under pressure politically, technologically, and socially.
Mapping these questions so systematically underlines the need for ethical reflection as a core competence in AI research – not after the fact, but as part of the epistemic and technical process.

#GenerativeAI
#AIethics
#ResponsibleAI
#EthicsInAI
#TechEthics
#AIresearch
#MachineLearning
#AIgovernance
#DigitalEthics
#AlgorithmicBias
#Disinformation
#SustainableAI
#InterdisciplinaryResearch
#ScienceAndSociety
#IRIS3D

formuchdeliberation

AI tackles notoriously complex equations, enabling faster advances in drug and material design – Tech Xplore…

These differential equations, such as Schrodinger's, can be solved analytically on a small scale, testing the dynamics of two particles, like electrons. As the number of particles being tested increases, the complexity of equations grows exponentially, making them impossible to solve for any systems of practically useful sizes... #ai #technology #machinelearning

formuchdeliberation.wordpress.

for much deliberation · AI tackles notoriously complex equations, enabling faster advances in drug and material design – Tech Xplore…These differential equations, such as Schrodinger’s, can be solved analytically on a small scale, testing the dynamics of two particles, like electrons. As the number of particles being teste…
Inkican

There's more than meets the eye to transformers. No, not that kind. Not that kind either.

arxiv.org/abs/2503.10622

arXiv logo
arXiv.orgTransformers without NormalizationNormalization layers are ubiquitous in modern neural networks and have long been considered essential. This work demonstrates that Transformers without normalization can achieve the same or better performance using a remarkably simple technique. We introduce Dynamic Tanh (DyT), an element-wise operation $DyT($x$) = \tanh(α$x$)$, as a drop-in replacement for normalization layers in Transformers. DyT is inspired by the observation that layer normalization in Transformers often produces tanh-like, $S$-shaped input-output mappings. By incorporating DyT, Transformers without normalization can match or exceed the performance of their normalized counterparts, mostly without hyperparameter tuning. We validate the effectiveness of Transformers with DyT across diverse settings, ranging from recognition to generation, supervised to self-supervised learning, and computer vision to language models. These findings challenge the conventional understanding that normalization layers are indispensable in modern neural networks, and offer new insights into their role in deep networks.
#artificialintelligence#ai#machinelearning
Michael Martinez :verified:

Don't use ChatGPT or other LLMs to summarize Google research papers. Especially don't do that for blog posts or presentations. If you don't understand the papers well enough to summarize them yourself, you're just going to look stupid letting an LLM mangle it for you.

#ai#llms#seo
TrendingLive feeds
About