Recent searches

No recent searches

Search options

Only available when logged in.
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.

Administered by:

Server stats:

218
active users

eupolicy.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#MachineLearning

59 posts55 participants8 posts today
Tanguy Fardet

I just discovered the ARC-AGI initiative and the associated test to estimate how close "AI" models are from #AGI

arcprize.org/arc-agi

While I found the initiative interesting, I'm not sure I understand what in this test really guarantees that the model is capable of some form of generalization and problem-solving.
Wouldn't it be possible for specialized pattern-matching/discovering algorithms to solve such problems?
I imagine some computer scientists, mathematicians or computational neuroscientists have already had a look at this, so would anyone knows of some articles/blogs on the topic?

Maybe @wim_v12e? Is this something you already looked at?

ARC PrizeARC Prize - What is ARC-AGI?The only AI benchmark that measures AGI progress.
#AI#machineLearning#neuroscience
*
Institute for AI

Is complex query answering really complex? A paper at the International Conference on Machine Learning (#ICML2025) presented by Cosimo Gregucci, PhD student at @UniStuttgartAI @Uni_Stuttgart, discussed this question.

In this paper, Cosimo Gregucci, Bo Xiong, Daniel Hernández (@daniel), Lorenzo Loconte, Pasquale Minervini (@pminervini), Steffen Staab, and Antonio Vergari (@nolovedeeplearning) reveal that the “good” performance of SoTA approaches predominantly comes from answers that can be boiled down to single link prediction. Current neural and hybrid solvers can exploit (different) forms of triple memorization to make complex queries much easier. The authors confirm this by reporting the performance of these methods in a stratified analysis and by proposing a hybrid solver, CQD-Hybrid, which, while being a simple extension of an old method like CQD, can be very competitive against other SoTA models.

The paper proposed a way to make query answering benchmarks more challenging in order to advance science.

arxiv.org/abs/2410.12537

#KnowledgeGraphs#QueryAnswering#ArtificialIntelligence
Stefano D'angello

Climate change isn't just an environmental issue; it's a looming public health crisis. Our latest research unveils a new framework that uses machine learning to predict climate-driven health emergencies, like heatwaves and disease outbreaks, with greater accuracy.
The goal: shift public health from being reactive to truly proactive.
Read the full paper here:
open.substack.com/pub/stefanod
#ClimateChange #PublicHealth #MachineLearning #AI #HealthTech #DataScience #PredictiveAnalytics #Epidemiology

HabileData

6 Essential Data Annotation Techniques that Drive Computer Vision

Our latest video on the 6 common types of annotation in Computer Vision reveals how the perfect blend of human intelligence and cutting-edge data annotation techniques can significantly enhance the performance and scalability of your AI and ML models.

youtube.com/watch?v=EHXVzz7VHvo

YouTube6 Essential Data Annotation Techniques for Your AI & ML Development SuccessBy Hitech BPO
#dataannotation#artificialintelligence#machinelearning
TrendingLive feeds
About