🚨 Job Alert 🚨
We're looking for a PhD student to strengthen our DataLab team
🔬: Data Analytics and AI for Decision Support
🎓: Relevant Msc: Computer Science, Economics, Engineering, Mathematics, Physics
All info at: https://t.co/jKKRstHwcv
#PhD#AI#WeAreVUB
Yesterday, we announced that the 2021 Best Paper Award is awarded to @VerbovenSam and @Niels_Martin for their paper "Combining the Clinical and Operational Perspectives in Heterogeneous Treatment Effect Inference in Healthcare Processes". Congratulations!
Het Data Analytics Laboratory is hiring! We zijn op zoek naar gemotiveerde kandidaten met een passie voor onderzoek en lesgeven. Word jij onze nieuwe collega?
https://t.co/3M7bQXeZgx
https://t.co/TwXQ029Qlt
Kandideren op beide vacatures is aangeraden.
Transplant organs are incredibly scarce, and each organ (like each patient) is unique. Matching patients to organs and estimating transplant effectiveness is a very complex and important problem we addressed in a recent paper, which you can find here: https://t.co/JPevtbtIF2
Woah wish I knew about this existed sooner: https://t.co/2y9yOtwSIV. Generates LaTeX for beautiful neural network visualizations (like the FCN-32 shown below).
Tomorrow first day of our #ijcai2020 workshop on Data Science meets Optimisation #DSO! Program: https://t.co/PKkmREZlRJ
Getting the Zoom link requires navigating IJCAI's https://t.co/shhdHwKB8f map to 'Red Wing, North 1'. The map is beautiful, but you have to get used to it!!
Can neural networks learn to perform explanatory & counterfactual reasoning? Researchers find that an object-centric transformer substantially outperforms leading neuro-symbolic models on two reasoning tasks thought to be challenging for deep neural nets: https://t.co/IchQKRDjRL
Machine learning finds an improved way to match donor organs with patients, potentially boosting survival time for the entire patient population. This is what the Cambridge Centre for AI in Medicine is all about. #NeurIPS2020#machinelearning#AI
https://t.co/boPSlandmI
🚨Announcement time! I've decided to start Inspiration Exchange, a series of regular discussion sessions for machine learning students. The first will happen on September 2 via @Zoom, and the main topic will be AutoML. The more the merrier—sign up here: https://t.co/ysn8L0zwVm
As communities have begun to recognize the importance of social distancing measures to “flatten the curve” on COVID-19 transmission, here’s a sober but useful primer on what we should expect in the coming months: https://t.co/9oqdRF5J0Q
me: I discovered a new statistical law that says that all jokes on twitter are based on other jokes on twitter
friend: that’s really cool! what do you call it?
me: *slowly takes off sun glasses* regression to the meme
New blog post: "A Recipe for Training Neural Networks" https://t.co/5lBy4J77aS a collection of attempted advice for training neural nets with a focus on how to structure that process over time
Style transfer without a specific style image. I minimize only the content loss from neural style transfer and directly optimize brushstrokes via backpropagation. In this case, "style" is an intrinsic property defined entirely by the artistic medium.
This is crazy. Study shoes three people in a conference room over 2 hours can result in a Co2 level that can impair cognitive functioning. Ie. If you’re making decisions at the end of the meeting, you’re mentally less qualified to do so.