Ben Wagner

@Okamizaka SORA

This is to prove that I genuinely have the Sora 2 invite code. People who RETWEET+LIKE will get FREE SORA 2 INVITE CODE. Comment "SORA" and make sure ur dm is open 📩

A practical tutorial on explainable AI techniques, thanks all contributors @BennetotA @ivandonadello @ayoub El Qadi, @maurodragoni @frossard_thomas , B Wagner, @Ann_Qnn , @si_tulli, @trocan_maria , @aHolzin, Raja Chatila, @AvilaGarcez dl.acm.org/doi/10.1145/36…

📢#NeSy 2024: 18th International Conference on Neural-Symbolic Learning and Reasoning (sites.google.com/view/nesy2024). Barcelona, Spain. September 9-12, 2024. Deadline full papers: April 12, 2024. @AvilaGarcez @jeublanc @NeSy_City

@tetraduzione @EmilevanKrieken @VUamsterdam Congratulations @EmilevanKrieken! Well deserved cum laude. Great stuff!

congrats to Dr. @EmilevanKrieken who successfully defended his #PhD thesis "#Optimization in #Neurosymbolic #Learning Systems" (research.vu.nl/en/publication…) obtaining a cum laude from @VUamsterdam! #ML #AI #NeSy

The heretofore silent majority of AI scientists and engineers who - do not believe in AI extinction scenarios or - believe we have agency in making AI powerful, reliable, and safe and - think the best way to do so is through open source AI platforms NEED TO SPEAK UP !

@EmilevanKrieken @PMinervini @tetraduzione @PontiEdoardo Congratulations on the submission! Will be exciting to see what you will continue to do with such a great team.

Dissertation... Submitted! I'm excited to start at the University of Edinburgh in September as a post-doc, working with the amazing @PMinervini @tetraduzione and @PontiEdoardo :)

New paper with Simon Odense on the semantics of neurosymbolic systems: arxiv.org/abs/2212.12050 Many approaches fall into the same semantic framework...

@AvilaGarcez Thank you very much for everything and happy easter.

Many congratulations to Dr @BeneWagner. Great PhD viva earlier this week and very nice thesis on reasoning about what has been learned! #NeSyAI

@twitemp1 Thank you very much. Really appreciate it!

The desired model behaviour will be reflected in the updated model parameters. This is accomplished with the use of Logic Tensor Networks as an approach for deep learning from data and knowledge in fully differentiable fuzzy logic.

In addition, the concepts may be used to impose new constraints onto the neural network, such as: the model should only recognise all horse-like objects with stripes as being zebras as long as the stripes are black and white.

Happy to introduce you to our latest work on taking a neural-symbolic approach to explainable AI with @AvilaGarcez published at NeurIPS 2021 Workshop on Human and Machine Decisions, arxiv.org/pdf/2112.11805…

@ejimenez_ruiz @CityUniLondon @CityUniSTEM @Cit_AI1 Congratulations, Ernesto!

Apparently I have been promoted to the "Top-3 AI 2000 Most Influential Scholars in Knowledge Engineering" over the past 10 years (2011–2020)" according to Aminer 😅 aminer.org/ai2000/ke @CityUniLondon @CityUniSTEM @Cit_AI1

We compare against fairness-based methods on 2 common notions of fairness across 3 three datasets. While the appropriateness of such notions are being discussed, the approach is adaptable and model-agnostic as LTN serve as a framework to complement explainability techniques

The Neural-Symbolic integration allows to not only better understand the decision-making process but also to intervene and act on extracted knowledge. We use First-Order-Logic constraints to adress these unwanted biases while retaining high predictive performance.

Happy to announce that our work (w/ @AvilaGarcez) on “Neural-Symbolic Integration for Fairness in AI” has been published at the AAAI 2021 Spring Symposium, AAAI-MAKE 2021: proceedings.aaai-make.info/AAAI-MAKE-PROC…