Géraldin Nanfack
@genanfack
Followers
92
Following
488
Media
0
Statuses
51
Postdoc @ University of Concordia & Mila
Namur, Belgium
Joined July 2017
Thrilled to share that our paper on "Adversarial Attacks on the Interpretation of Neuron Activation Maximization" has been accepted at AAAI'24. Exciting news: I'll be presenting a condensed version at ATTRIB 2023 Workshop (@ NeurIPS) in New Orleans next Friday!
0
4
16
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 !
@sriramk yes - the deck is stacked Decades of dystopian sci-fi and talk of extinction create the fear required to limit development open-source advocates need clear, tangible examples of the tech's value and the importance of US leadership who do you think is doing this best?
154
383
2K
En l'honneur de #Juneteenth, le collectif des Noir⋅e⋅s à Mila vous invite à son événement de lancement le 16 juin pour célébrer les réalisations et les contributions académiques des chercheur⋅e⋅s noir⋅e⋅s en #IA ! Réservez votre place 👉 https://t.co/F1znHpe1ci
0
3
6
In honour of #Juneteenth, the Black at Mila Collective is inviting you to its launch event on June 16, celebrating the academic achievements and contributions of Black researchers in #AI ! Book your spot 👉 https://t.co/RbyGLDfPzD
1
6
31
I'd like to have a real conversation about whether AI is a risk for human extinction. Honestly, I don't get how AI poses this risk. What are your thoughts? And, who do you think has a thoughtful perspective on how AI poses this risk that I should talk to?
666
674
4K
1/The call for a 6 month moratorium on making AI progress beyond GPT-4 is a terrible idea. I'm seeing many new applications in education, healthcare, food, ... that'll help many people. Improving GPT-4 will help. Lets balance the huge value AI is creating vs. realistic risks.
340
2K
8K
On 24 November, Géraldin NANFACK @genanfack presented his doctoral thesis "Constraint Enforcement on Decision Trees and its Application to Global Explainability Supervised by @benoitfrenay and @pleupi22 Congratulations to Géraldin NANFACK ! 👏
0
4
5
Congrats, Dr. @genanfack for your PhD defense on Constraint Enforcement on Decision Trees and its Application to Global Explainability! @NADI_institute @UNamurCSFaculty (funded by @frsFNRS through EOS VeriLearn)
0
4
13
I had the chance to supervise @genanfack who defended his PhD today. What a gratitude to @GPerrouin @benoitfrenay @UNamurCSFaculty and such a nice experience to contemplate what PhD student can achieve in a few years. All the best to you Dr @genanfack for your post-doc and after
@genanfack is defending his PhD defense on constraint enforcement on decision trees. promoters: @benoitfrenay @pleupi22
1
2
13
Félicitations. Fan de ta tenue @genanfack
@genanfack is defending his PhD defense on constraint enforcement on decision trees. promoters: @benoitfrenay @pleupi22
1
1
6
I am very proud 😃 to have privately defended my PhD thesis. Public defence is scheduled for the 24th of November. Thank you to members of my jury and particularly my supervisors @benoitfrenay and @pleupi22.
0
2
14
AI fashion show using dall-e to generate hundreds of outfits of the day after tomorrow. An interesting way to brainstorm costume and fashion design ideas. Collab with @shyamagolden
@OpenAI #dalle2 #dalle #aiart
150
1K
6K
We (@BeEngelhardt, @NailaMurray and I) are proud to announce the creation of a Journal-to-Conference track, in collaboration with JMLR and conferences NeurIPS 2022, ICLR 2023 and ICML 2023! https://t.co/DYcKRBDOw1
https://t.co/Er3jLzPXf4
https://t.co/DMfKbMukpd
18
194
1K
We are glad to see our #openaccess survey published on ACM Computing Surveys about constraint enforcement on decision trees with @genanfack, @pleupi22 and @benoitfrenay at @UNamurCSFaculty thanks to @frsFNRS. #ACMSurvey #DecisionTree #Constraints
https://t.co/YATdZYmVzC (1/3)
1
6
9
We are proud to introduce two new Sign Language datasets, some of the largest available in terms of video length. Also battery-included: Python interface available! #IJCNN #ComputerVision #LSFB @jefidev @anthonycleve @UNamurCSFaculty @UNamur
https://t.co/IY2XWN2llJ (1/n)
1
8
13
Check out our latest research https://t.co/7NTsFLrR8W We developed an eXplainable AI toolkit for responsible evaluation of neural network explanations, including a growing collection of 25+ evaluation metrics and comprehensive guidance on how to use them https://t.co/Ymwx9pR0Ti
1
9
28
I am delighted to announce that my new book, “Probabilistic Machine Learning: An Introduction”, is finally available in print format! You can order it from https://t.co/fx92WBQvk3, or from Amazon. Also available at https://t.co/dSlKkwYpLr 1/4
42
462
3K
got also a J1st accepted @ICSAconf ; the opportunity for us to make our work about using adversarial ML to generate automatically new configurations ( https://t.co/otB6JCXVCp) more popular in a related community =)
1
5
16
@genanfack got 2 papers accepted by the end of 2021: - a survey at Computing Surveys ( https://t.co/gdH57V7YYR) - a paper about explanations with decision rules at UAI ( https://t.co/Xx473ToFpi)
dl.acm.org
Decision trees have the particularity of being machine learning models that are visually easy to interpret and understand. Therefore, they are primarily suited for sensitive domains like medical...
1
3
7
Today, @RaiaHadsell, @kchonyc and I are happy to announce the creation of a new journal: Transaction on Machine Learning Research (TMLR) Learn more in our post:
51
656
2K