ML query language, by ML, caveat emptor (it's really LM)
textblock
Introducing MLQL – a query language for ML models. Think SQL, but for predictions, explanations, and comparisons. Example:
PREDICT churn USING model churn_model WHERE region="EU" EXPLAIN top_features.
Supports raw input, filters, explanations like SHAP. Stop treating ML like a black box.
#ML #AI #DevTools #ExplainableAI #MastodonDelendaEst
textblock
"Finally, AI can fact-check itself. One large language model-based chatbot can now trace its outputs to the exact original data sources that informed them.
Developed by the Allen Institute for Artificial Intelligence (Ai2), OLMoTrace, a new feature in the Ai2 Playground, pinpoints data sources behind text responses from any model in the OLMo (Open Language Model) project.
OLMoTrace identifies the exact pre-training document behind a response — including full, direct quote matches. It also provides source links. To do so, the underlying technology uses a process called “exact-match search” or “string matching.”
“We introduced OLMoTrace to help people understand why LLMs say the things they do from the lens of their training data,” Jiacheng Liu, a University of Washington Ph.D. candidate and Ai2 researcher, told The New Stack.
“By showing that a lot of things generated by LLMs are traceable back to their training data, we are opening up the black boxes of how LLMs work, increasing transparency and our trust in them,” he added.
To date, no other chatbot on the market provides the ability to trace a model’s response back to specific sources used within its training data. This makes the news a big stride for AI visibility and transparency."
https://thenewstack.io/llms-can-now-trace-their-outputs-to-specific-training-data/
AI in Banking Security: Revolution & Risks
#TycoonWorld #AIinBanking #BankingSecurity #CyberSecurityAI #FinTechSecurity #ArtificialIntelligence #MachineLearning #AnomalyDetection #BehavioralAnalytics #ThreatDetection #FraudPrevention #PredictiveAnalytics #EthicalAI #DataPrivacy #ExplainableAI #AdversarialAttacks #BankingInnovation #FinancialSecurity #AIethics #AIrisks #DigitalBanking #AIinFinance #AIandCybercrime #SmartBanking #FinTechTrends #CyberRiskMitigation
https://tycoonworld.in/ai-in-banking-security-revolution-risks/
Tohoku University's 110MB AI glaucoma detection system demonstrates clinical viability with 93.5% sensitivity, backed by Japan's $12M rural health initiative. 
As AI becomes central to bioinformatics, the opacity of its decision-making remains a major concern.
We did it! We selected the 61 best students from the overall more than 100 applications. Due to always possible visa issues and other unfortunate circumstances for late cancellations, we've also created a waiting list for potential additional candidates. Congratulations to all of you!!
Looking forward to meeting you all in Bertinoro in June!
A big thank you to all speakers, participants & organizers! 
Are you passionate about the latest in #AI? Here's your chance to shine!
Which AI topic are you most excited to explore?
Explore topics like #LLMs, #SLMs, #vLLMs, #GenAI, #VectorDatabases, #ExplainableAI, #RAG, and more!
Are you passionate about the latest in #AI? Here's your chance to shine!
Which AI topic are you most excited to explore?
Explore topics like #LLMs, #SLMs, #vLLMs, #GenAI, #VectorDatabases, #ExplainableAI, #RAG, and more!
Applications are now open for the 2025 International Semantic Web Research Summer School - #ISWS2025
in Bertinoro, Italy, from June 8-14, 2025
Topic: Knowledge Graphs for Reliable AI
Application Deadline: March 25, 2025
Webpage: https://2025.semanticwebschool.org/
Great keynote speakers: Frank van Harmelen (VU), Natasha Noy (Google), Enrico Motta (KMI)
#semanticweb #knowledgegraphs #AI #generativeAI #responsibleAI #explainableAI #reliableAI @albertmeronyo @AxelPolleres @lysander07
Excited to attend my first PhD defence at TU Delft: Daniël Vos will be defending his thesis "Decision Tree Learning: Algorithms for Robust Prediction and Policy Optimization", containing work he did under supervision of Prof. Dr. Ir. R.L. Lagendijk and Dr. Ir. Sicco Verwer.
Not blackbox but an an explainable AI model
#AI #explainableAI #nature
https://www.nature.com/articles/s41596-024-01084-x
[Neue Publikation] Wir untersuchten, ob die KI in der Lage ist, subtile morphologische Unterschiede zwischen verschiedenen Populationen anhand von einfachen Smartphone-Aufnahmen zu erkennen. Die Ergebnisse zeigen: Ja, die KI kann selbst bei komplexen Bildhintergründen zuverlässig charakteristische Merkmale der Blätter identifizieren. #explainableAI #XAI #FloraIncognita
Mehr Details: https://floraincognita.de/neue-publikation-erkennt-eine-kuenstliche-intelligenz-die-blattform/
This Friday at 12.15 CEST I'll be hosting a talk by computer scientist Kary Främling, in which he will present his work on Explainable AI techniques for producing explanations useful to a variety of stakeholders, rather than only to AI experts.
The talk is hybrid, so even if you are not currently enjoying the very colourful (and very wet) autumn in Umeå, you can join nonetheless!
More information here: https://www.umu.se/en/events/fraiday-social-explainable-ai-how-can-we-make-it-happen-_11985341/
All welcome!
We have an exciting main event at #HCXAI at #chi2024 today!
We have @janethaven from @datasociety and
Kush Varshney from @ibmresearch for an invigorating discussion on AI governance and policymaking to take Explainable AI beyond academia.
Can anyone suggest a good (as in accessible for non-specialist readers) article on calibrated trust and AI systems? It's for our @BL_DigiSchol reading group, where papers with equations can be offputting
