Tootfinder

This https://arxiv.org/abs/2404.05582 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning Prehensile Dexterity by Imitating and Emulating State-only Observations
When humans learn physical skills (e.g., learn to play tennis), we tend to first observe and learn what an expert is doing. But this is often insufficient. Therefore, we subsequently engage in practice, where we try to emulate the expert. Inspired by this observation, we introduce Combining IMitation and Emulation for Motion Refinement (CIMER) -- a two-stage framework to learn dexterous prehensile manipulation skills from state-only observations. CIMER's first stage involves imitation: simultan…

Function Class Learning with Genetic Programming: Towards Explainable Meta Learning for Tumor Growth Functionals
E. M. C. Sijben, J. C. Jansen, P. A. N. Bosman, T. Alderliesten
https://arxiv.org/abs/2402.12510 https://arxiv.org/pdf/2402.12510
arXiv:2402.12510v1 Announce Type: new
Abstract: Paragangliomas are rare, primarily slow-growing tumors for which the underlying growth pattern is unknown. Therefore, determining the best care for a patient is hard. Currently, if no significant tumor growth is observed, treatment is often delayed, as treatment itself is not without risk. However, by doing so, the risk of (irreversible) adverse effects due to tumor growth may increase. Being able to predict the growth accurately could assist in determining whether a patient will need treatment during their lifetime and, if so, the timing of this treatment. The aim of this work is to learn the general underlying growth pattern of paragangliomas from multiple tumor growth data sets, in which each data set contains a tumor's volume over time. To do so, we propose a novel approach based on genetic programming to learn a function class, i.e., a parameterized function that can be fit anew for each tumor. We do so in a unique, multi-modal, multi-objective fashion to find multiple potentially in- teresting function classes in a single run. We evaluate our approach on a synthetic and a real-world data set. By analyzing the resulting function classes, we can effectively explain the general patterns in the data.

Oracle's controversial stewardship of Java: The good and the bad.
Oracle is doing a good job in keeping Java relevant. But that's pretty much where it ends, says Azul CTO (free reg)
https://www.computing.co.uk/feature/4172927/or…

Oracle's controversial stewardship of Java: The good and the bad
Once upon a time, every developer looking for a top wage was urged to learn Java, the language of business. But that was quite a while ago. Business has plenty of other languages and Java could have fallen by the wayside, and it's to Oracle's credit that Java remains popular and highly relevant today, says Simon Rutter deputy CTO Azul.

Function Class Learning with Genetic Programming: Towards Explainable Meta Learning for Tumor Growth Functionals
E. M. C. Sijben, J. C. Jansen, P. A. N. Bosman, T. Alderliesten
https://arxiv.org/abs/2402.12510 https://arxiv.org/pdf/2402.12510
arXiv:2402.12510v1 Announce Type: new
Abstract: Paragangliomas are rare, primarily slow-growing tumors for which the underlying growth pattern is unknown. Therefore, determining the best care for a patient is hard. Currently, if no significant tumor growth is observed, treatment is often delayed, as treatment itself is not without risk. However, by doing so, the risk of (irreversible) adverse effects due to tumor growth may increase. Being able to predict the growth accurately could assist in determining whether a patient will need treatment during their lifetime and, if so, the timing of this treatment. The aim of this work is to learn the general underlying growth pattern of paragangliomas from multiple tumor growth data sets, in which each data set contains a tumor's volume over time. To do so, we propose a novel approach based on genetic programming to learn a function class, i.e., a parameterized function that can be fit anew for each tumor. We do so in a unique, multi-modal, multi-objective fashion to find multiple potentially in- teresting function classes in a single run. We evaluate our approach on a synthetic and a real-world data set. By analyzing the resulting function classes, we can effectively explain the general patterns in the data.