I’m a Dr.! (phD) 📜👩🏼‍💻

I thought this was just going to be cute (it was) but it was also poetic and moving

Some thoughts and takeaways from this paper: (1/4) Health systems tend to treat physical and mental health as two totally separate things, but people often have both and experience them as interconnected.

📣 🗞️ 👉 Just in time for Mental Health Awareness Week 🧠 🎉Our study is now published in Nature Comms Medicine! ⚡ We look at whether certain patterns of physical conditions affect the risk of developing #depression 📜 Paper: www.nature.com/articles/s43... 🖥️ Post: www.ed.ac.uk/news/multipl...

New Python package for scalable association rule mining! We propose a novel neurosymbolic method for scalable rule mining from tabular data that can be used for both knowledge discovery and fully interpretable inference. 🧩 github.com/DiTEC-projec... 📜 arxiv.org/pdf/2504.19354 🧵1/5

Cloudflare have developed a way to trap bots scraping the internet for AI data in a honeypot labyrinth. Hilariously, they used AI to generate realistic-looking webpages that have many many many links and can trap AI scraping bots in place:

There is something inhuman in quantifying and optimizing things that I can not pinpoint. It is not only that we miss-quantity the unquantifiable or misrepresent the intangible to pursue as goals, but deeper. It is depressing to think every human institution rests on quantification and optimization.

Go catch @neuralnoise.com in London!

A friend included this anti-acknowledgement section on her PhD thesis. She also added the proposition: “Systematic bullying and undermining of girls and women in STEM starts early on and is the reason why they do not stay in science and related fields.” Absurd we still need to go through this 🧪👩‍🔬

Let's talk about this Nature piece in more detail. I've rarely read something so anti-scientific anywhere short of the National Review. www.nature.com/articles/d41...

RL is so back! (well, for some of us, it never really left) awards.acm.org/about/2024-t...

The inspo I needed this morning 🫶

🔥 Can AI reason over time while following logical rules in relational domains? We will present Relational Neurosymbolic Markov Models (NeSy-MMs) next week at #AAAI2025! 🎉 📜 Paper: arxiv.org/pdf/2412.13023 💻 Code: github.com/ML-KULeuven/... 🧵⬇️

I've become a superpredictor just through this rule of thumb: future AI will improve faster than you think, but current capabilities are always exaggerated. Another example from @danishpruthi.bsky.social

This excellent Nature paper from 2015 discussed multiple ways that sex is not binary, and why the idea of two sexes is simplistic. Required reading right now - please share! www.nature.com/articles/518... 🧪👨‍🔬🧬🖥️

I have work to do but I'm distracted by watching US scientific progress & leadership being irreversibly undermined because a few unelected malcontents are penalizing researchers for following legal requirements set out by congressional orders to augment basic research with benefits to society.

Recs for VSCode extensions that auto-format code?

OMG. You cannot make this up. February 8, 2023: “Alphabet stock plunge erases $100 billion after new AI chatbot gives wrong answer in ad” February 6, 2025: “Google edits Super Bowl ad for AI that features false information” Exponential progress, my eye.

New: The largest medical A.I. randomized controlled trial yet performed, enrolling >100,000 women undergoing mammography screening The use of AI led to 29% higher detection of cancer, no increase of false positives, and reduced workload compared with radiologists w/o AI thelancet.com/journals/lan...

I am prepared to buy MORE LEGO to assist the Danish economy should it prove necessary.

The enigma machine 😳 and the cofee machine 😌

Exciting new partnership in AI & Life Sciences announced today in Brussels

This explains how Avatar Aang was preserved in an iceberg for 100 years journals.plos.org/plosgenetics...

We gave MARS💊👽 (arxiv.org/abs/2410.05289) a makeover with better figures. Look how much better this one is already!!

My first morning run in London 🎡 , ready to start at the Alan Turing Institute this week 🙌🏼

A common issue I see in ML, both from ML "experts" and "users", is overly optimistic assumptions. "experts" (people designing algs) usually assume the data is very simple "users" (people using algs) usually assume that algorithms are more robust than they really are Conclusion: always be careful!

Ever wondered why presenting more facts can sometimes *worsen* disagreements, even among rational people? 🤔 It turns out, Bayesian reasoning has some surprising answers - no cognitive biases needed! Let's explore this fascinating paradox quickly ☺️

Especially frustrating when you’re job-seeking and the “preferred qualifications” lists e.g., extensive experience in one discipline but papers in top venues for the other 🥲 h e l p

RIP to Felix Hill. We overlapped at Cambridge ages ago but I remember him as an ebullient and witty conversationalist, plus kind and introspective. His blog post is relevant to anyone, even if not directly working in AI, experiencing stress from the pace of research <3 medium.com/@felixhill/2...

“the future of AI should focus on neuro-symbolic systems, which combine the learning capabilities of deep learning with the structured, rule-based reasoning of symbolic AI “ —

What should I do if a reviewer says they’ll raise their score now, but they haven’t done so? 🫣

What artistic genius designed this

Moving to 🦋 from the dark place has been overwhelming- still working on finding people- sorry if I haven’t followed back yet😬

👋🏼 Hello, 🦋! Let me re-introduce myself. I’m a PhD student at @uoe-sps.bsky.social 🏴󠁧󠁢󠁳󠁣󠁴󠁿 researching #Neurosymbolic AI for #Biomedical Applications 🌱💊