Tootfinder

Bahnhöfe: Was Flensburg von Tornesch und Büchen lernen kann
Wie mögen wohl Bahnhöfe in Thüringen oder Westfalen aussehen, wenn Schleswig-Holsteins Stationen bundesweit Bestnoten bekommen?
https://www.shz.de/deutschland-w…

Bahnhöfe: Was Flensburg von Tornesch und Büchen lernen kann
Wie mögen wohl Bahnhöfe in Thüringen oder Westfalen aussehen, wenn Schleswig-Holsteins Stationen bundesweit Bestnoten bekommen?

Action Model Learning with Guarantees
Diego Aineto, Enrico Scala
https://arxiv.org/abs/2404.09631 https://arxiv.org/pdf/2404.09631

Action Model Learning with Guarantees
This paper studies the problem of action model learning with full observability. Following the learning by search paradigm by Mitchell, we develop a theory for action model learning based on version spaces that interprets the task as search for hypothesis that are consistent with the learning examples. Our theoretical findings are instantiated in an online algorithm that maintains a compact representation of all solutions of the problem. Among these range of solutions, we bring attention to act…

Heather Flanagan from Spherical Cow Consulting joined our podcast to give us an insight into her #TNC24 session ‘Inside the Classroom’, which will dive into the world of educational technology.
Listen to the episode now:
On Spotify:

In the Classroom - Heather Flanagan
Listen to this episode from Get Ready for TNC on Spotify. This session dives into the world of educational technology, exploring the transformative impact of digital credentials on the European educational landscape, the orchestrated deployment of virtual labs for immersive learning experiences, and the innovative integration of Jupyter Notebooks with SUNET Drive for enhanced research and teaching. Join us to discover how these advancements are reshaping learning, validation, and collaboration …

Implementing engrams from a machine learning perspective: XOR as a basic motif
Jesus Marco de Lucas, Maria Pe\~na Fernandez, Lara Lloret Iglesias
https://arxiv.org/abs/2406.09940 …

Implementing engrams from a machine learning perspective: XOR as a basic motif
We have previously presented the idea of how complex multimodal information could be represented in our brains in a compressed form, following mechanisms similar to those employed in machine learning tools, like autoencoders. In this short comment note we reflect, mainly with a didactical purpose, upon the basic question for a biological implementation: what could be the mechanism working as a loss function, and how it could be connected to a neuronal network providing the required feedback to …

Are we allowed to fail? We are told to learn from our failures...but how? Join the first keynote session at #TNC24 on Tuesday 11 June by Paul Iske on Brilliant Failures: Working together, failing together, #learning together.
Take a look at the programme
👉

On the Power of Interactive Proofs for Learning
Tom Gur, Mohammad Mahdi Jahanara, Mohammad Mahdi Khodabandeh, Ninad Rajgopal, Bahar Salamatian, Igor Shinkar
https://arxiv.org/abs/2404.08158

On the Power of Interactive Proofs for Learning
We continue the study of doubly-efficient proof systems for verifying agnostic PAC learning, for which we obtain the following results. - We construct an interactive protocol for learning the $t$ largest Fourier characters of a given function $f \colon \{0,1\}^n \to \{0,1\}$ up to an arbitrarily small error, wherein the verifier uses $\mathsf{poly}(t)$ random examples. This improves upon the Interactive Goldreich-Levin protocol of Goldwasser, Rothblum, Shafer, and Yehudayoff (ITCS 2021) whose…

Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households
Zhihao Cao, Zidong Wang, Siwen Xie, Anji Liu, Lifeng Fan
https://arxiv.org/abs/2404.09001

Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households
Despite the significant demand for assistive technology among vulnerable groups (e.g., the elderly, children, and the disabled) in daily tasks, research into advanced AI-driven assistive solutions that genuinely accommodate their diverse needs remains sparse. Traditional human-machine interaction tasks often require machines to simply help without nuanced consideration of human abilities and feelings, such as their opportunity for practice and learning, sense of self-improvement, and self-estee…

Some friend told me that learning to program was a waste of time since AI would write all perfect code for us and make most developers obsolete within 3 years...
It is now exactly 3 years ago, how are my developer homies holding up? Feeling obsolete yet? :yay:

🧵 Thread: Re-plugging an old article that my friend, mentee and former colleague Mythri Prabhakara wrote about learning digital security over approximately 8 months while navigating her #neurodivergence and other intersectional identities, and a pandemic to boot.
(I’ve shared an archived link because the footnotes and text currently displaying are a bit weird.)

Learning digital security as a “non-techie”
A wooden duster came flying at 11-year-old me. I had misspelled my Venn diagram as “when diagram”, and the math teacher was teaching me an important lesson. Although not officially a part of the syllabus, my place within the classroom was clear. I was, as she called me, a pedhi.Kannada (Dravidian language spoken predominantly by the people of Karnataka in the southwestern