Ben Wagner

Lecturer (Asst. Professor) | AI Research | Data Science | London
[email protected]

[Ben Wagner @BeneWagner]

@Okamizaka SORA

[Natalia Díaz Rodríguez, PhD #TrustworthyAI @NataliaDiazRodr]

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
https://t.co/3FZWkyn27Y

[Ernesto Jimenez-Ruiz @ejimenez_ruiz]

📢#NeSy 2024: 18th International Conference on Neural-Symbolic Learning and Reasoning (https://t.co/rZna4T7wXd). Barcelona, Spain. September 9-12, 2024.
Deadline full papers: April 12, 2024.
@AvilaGarcez
@jeublanc
@NeSy_City

[Ben Wagner @BeneWagner]

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

[Yann LeCun @ylecun]

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 !

[Ben Wagner @BeneWagner]

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

[Artur d'Avila Garcez @AvilaGarcez]

New paper with Simon Odense on the semantics of neurosymbolic systems:
https://t.co/HZMVmbKJPi
Many approaches fall into the same semantic framework...

[Ben Wagner @BeneWagner]

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

[Artur d'Avila Garcez @AvilaGarcez]

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

[Ben Wagner @BeneWagner]

@twitemp1 Thank you very much. Really appreciate it!

[Ben Wagner @BeneWagner]

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.

[Ben Wagner @BeneWagner]

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,
https://t.co/W6qB44GzWJ

[Ben Wagner @BeneWagner]

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.

[Ben Wagner @BeneWagner]

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

[Ben Wagner @BeneWagner]

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

[Ben Wagner @BeneWagner]

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: https://t.co/Ik4Xt1TTI1

[Ben Wagner @BeneWagner]

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.