PhD @GatsbyUCL, neuro/ML theory | Clinician | TA @CompNeuroImbizo | Organiser @DeepIndaba | healthcare @AmathamboAI | Prev. @OISTedu, @UCT_NI | Exploring 🇿🇦
London, England
Joined March 2013
- Tweets440
- Following607
- Followers668
- Likes908
Kira Düsterwald retweeted
Recharged and ready!🔋
After a massive first week and a well-deserved day off surfing🏄♂️ and visiting the penguins🐧, we are back in the classroom.
We are thrilled to kick off Cycle 2 today with @alfairhall as our Academic Director!
@SimonsFdn @IBROorg
ALT Sunset seen from the Chapman's Peak.
ALT Walk towards the wreck of the kakapo, Noordhoek, South Africa
ALT Surfing team before their lesson
ALT (Some) of the penguin team members.
Kira Düsterwald retweeted
A massive shoutout to our incredible mentors and TAs! 🙌 They delivered 6 wonderful tutorials. Their energy and dedication make this school special.💻🧠🇿🇦
@spiroschv | @kiradusterwald | @dorrell_will | @isabelmaria_c | Colleen Gillon | @rherzoga
ALT A collage showing six Imbizo mentors teaching their tutorials: Spiros Chavlis on Python and LIF models, Will Dorrell on neural computation, Kira Düsterwald on Probability Theory, Isabel Cornacchia on Dynamical Systems, Colleen Gillon on Reinforcement Learning, and Rubén Herzog on Information Theory.
Kira Düsterwald retweeted
This is the moment of the year we’ve been waiting for! 🌍🧠
We are thrilled to welcome you to Noordhoek, Cape Town, for another amazing Imbizo school. Can’t wait to gather, share knowledge, and dive deep into computational neuroscience!
Let the learning begin! 🇿🇦✨ #imbizo2026
Kira Düsterwald retweeted
Remembering Adam Kampff, a dear friend, inspirational teacher, and a remarkable human being. He dedicated his life to broadening scientific education and demystifying modern technology to young people around the world.
sainsburywellcome.org/web/re…
Kira Düsterwald retweeted
✈️ Heading to #SfN25?
Check out Kira Dusterwald's work
"Autistic individuals learn to exploit temporal regularities in simple but not complex contexts"
at Early Career Poster Session (Nov 15 18:45-20:45, A21) or Autism: Behavioral Analysis session (Nov 16 13-17, A27).
Kira Düsterwald retweeted
🙋Are you interested in bridging theory & experiments?
Applications are now open for 2026 entry to the Gatsby Unit & SWC (@SWC_Neuro) joint PhD programme.
Join us and be part of a vibrant research community!
💰 Fully-funded 4-year programme
ℹ️ ucl.ac.uk/life-sciences/gats…
Kira Düsterwald retweeted
Interested in a #PhD in machine learning & theoretical neuroscience?
Applications for 2026 entry to the Gatsby Unit PhD programme are now open!
💰 Fully-funded 4-year programme
🤝 Close links to @SWC_Neuro & @uclcsml
ℹ️ ucl.ac.uk/life-sciences/gats…
Kira Düsterwald retweeted
The opportunity gap in AI is more striking than ever. We talk way too much about those receiving $100M or whatever for their jobs, but not enough those asking for <$1k to present their work.
For 3rd year in a row, @ml_collective is raising funds to support @DeepIndaba attendees.
🤩💫🇿🇦 @smhall97
Meet @smhall97 , a dedicated member of the Deep Learning Indaba community making a real impact! 📷
Based between South Africa and the UK, Siobhan's journey with the Indaba began in 2018, and her commitment has grown ever since as she has contributed in numerous vital roles for the organisation.
Starting as a physiotherapist in South Africa, the Deep Learning Indaba ignited a passion for coding and deep learning in 2018, catalysing a remarkable transition into AI research. Since 2019, she has worked in data science and computational neuroscience, ultimately finding her focus in advocating fairness in AI.
Driven by the powerful sense of community experienced at her first Indaba in 2018, she joined to contribute to this incredible movement and pay forward many of the opportunities the Indaba has helped her pursue.
Siobhan is also deeply involved in the fascinating project "World Wide Dishes," operationalising bias and fairness through the lens of food as culture.
Learn more here: worldwidedishes.com/ and explore her related research here: dl.acm.org/doi/10.1145/37152…
Kira Düsterwald retweeted
🎉🚨 Extended Application Deadline! Now July 16, 2025!
If you want to learn about the brain💻🧠in the amazing Noordhoek, Cape Town🇿🇦, apply.
What to Do Next: Finalise and submit applications before the deadline: imbizo.africa/apply/
Please spread the news. Don’t miss out!
Kira Düsterwald retweeted
The Data Science and Machine Learning Unit (@myamada0) at OIST is working to improve the algorithms of the information age and how we interact with AI💻⚙ They had 5 papers – 4 written by interns – accepted at the recent #ICLR2025. Learn about the unit 👇 oist.jp/news-center/news/202…
Kira Düsterwald retweeted
Want to spend 3 weeks in South Africa🇿🇦for an unforgettable summer school experience? Imbizo 2026 (imbizo.africa) student applications are OPEN! 💻🏄♀️ Lectures, new friends, and Noordhoek beach await. Apply by July 1!
🖇️imbizo.africa/apply/
#Imbizo2026 #CompNeuro
Looking forward to presenting Tree-WSV for fast unsupervised ground metric learning at @iclr_conf 2025 tomorrow at 3 pm! Come find me at poster #197 🌳
New preprint! 🚨 Clustering is a powerful tool in genomics & neurosci, but is contingent on the distance /cost chosen between data features. With @samo_hromadka & @myamada0 we used optimal transport on trees 🌳 to learn underlying distances – fast! arxiv.org/abs/2411.07432 1/8
Kira Düsterwald retweeted
We’re happy to share that members of our MLDS unit (@OISTedu) will present several papers at #ICLR2025!
Topics include brain-inspired representation learning, optimal transport, decentralized learning, anomaly detection, and LLM uncertainty quantification.
Feel free to stop by our posters if you're around!
🌳 Kira M Düsterwald, Samo Hromadka, & Makoto Yamada. Fast unsupervised ground metric learning with tree-Wasserstein distance.
openreview.net/forum?id=FBhK…
@kiradusterwald
🕵️♂️ Hossein Mirzaei, Mojtaba Nafez, Jafar Habibi, Mohammad Sabokrou, & Mohammad Hossein Rohban. Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation
openreview.net/forum?id=t8fu…
@sabokrou
🧠 Satoki Ishikawa, Makoto Yamada, Han Bao, & Yuki Takezawa. PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis.
openreview.net/forum?id=5tjd…
@SisForCollege @levelfour_ @YukiTakeza
🚀 Siqi Zeng, Sixian Du, Makoto Yamada, & Han Zhao. Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport.
openreview.net/forum?id=AnL6…
@cindy2000_sh @hanzhao_ml
🌐 Yuki Takezawa, & Sebastian Stich. Scalable Decentralized Learning with Teleportation.
openreview.net/forum?id=AvmB…
@YukiTakeza
🤖 Daniel Yang, Yao-Hung Hubert Tsai, & Makoto Yamada, On Verbalized Confidence Scores for LLMs
(ICLR 2025 workshop on Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI)
openreview.net/forum?id=CVRd…
Kira Düsterwald retweeted
I'm excited to announce that I have received the Thuthuka Research Grant from the @NRF_News! I will use this grant to start my own lab focused on comp neuro and ML theory at @WitsUniversity: the @caandl_lab! This is a joint effort with @VictoriaWi83762, @stefsmlab and @geraudnt.
Kira Düsterwald retweeted
PS to any going through personal issues while finishing a paper, take the time to heal. I'm supremely grateful to my collaborators for their patience & support as I heal. I know that's not universal, but your health should always come first. Don't let anyone tell you otherwise.
Kira Düsterwald retweeted
Transformers employ different strategies through training to minimize loss, but how do these tradeoff and why?
Excited to share our newest work, where we show remarkably rich competitive and cooperative interactions (termed "coopetition") as a transformer learns.
Read on 🔎⏬
Kira Düsterwald retweeted
Meet @kiradusterwald , our keynotes committee chair for #DLI2025 !
Her journey started at @UCT_news , where she balanced studying medicine with a passion for pure maths. After earning her Honours and Masters in neuronal modelling, she's now diving into theoretical neuroscience and machine learning as a PhD candidate at @ucl .
Kira has been an inspiring part of the Indaba since 2017, taking part of our programme committee, getting involved with tutoring, developing practicals and now helping with keynotes.
Catch up on Kira's recent work in optimal transport theory: 👉arxiv.org/pdf/2411.07432
