### SK From [[def(Digital Twin)]] - Can PL be used to help identify/alleviate problems in computation(e.g: using PL as a tool for realizing mathematically defined conditions)? If not, can we view them as mutually exclusive? - I think Martin's current research (finding what quantities we need to generate) may be related to PL. This is just a speculation, since I have no idea what form $f$ will be. But creating generated quantities from a model strongly suggests needing to work with a structured representation of a model. From [[22.05.19.SBCmeeting]], #RB ### AM From [[🏭def(generate)]], the meaning of `probability`? > standard convolutional classifier which takes an image and `down-samples` it to produce a probability. #AH ### horseshoe prior > debate between Bayesian and likelihood solutions is quite muted, with a recommendation for weakly informative priors superseded by the call for exploring the impact of one’s assumption. (Although the horseshoe prior makes an appearance, p.209!) Why is horseshoe prior a counterexample for weak informative prior superseding impact for one's assumption? from [[BookQuotes]] ### improperness at infinity? > Chp.5 broaches on improper posteriors by suggesting to run a Markov chain that can exhibit improperness by enjoying an improper behaviour. When it happens as in the quote above, fine!, but there is no guarantee this is always the case! For instance, improperness may be due to regions near zero rather than infinity. from [[BookQuotes]] --- statistical ordering via likelihood ratio, harzard rate, stochastic ordering (weak, in distribution), icx (only increasing convvex) Every increasing function Using stochastic ordering two mappings f, g that are in order-unpreserving transform relation has $S_f \setminus S_g \neq \emptyset, S_g \setminus S_f \neq \emptyset$ > justifying oracle hierarchy; finding a test function (experiment and theory) > ### Algorithm as an object > symmetry of an object is a transformation of that object which  leaves it unchanged ![[Pasted image 20220528100337.png]] - Do we have Monte Carlo operator? - an operator that approximate every continuous process to point process - Sorting algorithm has symmetry (permutation invariant) From [[🌌⏳ 2Space times 3Time]] - Is coupling equivalent to hierarchical structure in that they share the marginal but has different joint. Increasing level of coin 🪙 = assuming greater things (more freezing 🥶)= hierarchical modeling 🪙 axiom 🪙🪙 axiom-system 🪙🪙🪙 axiom-system-alg ![[Pasted image 20220518171445.png]] From [[def(Digital Twin)]] - From "diagnostic tools, such as SBC, an aleatoric "model" of epistemic uncertainty" Why is diagnostic tool a model of uncertainty? How do you define model? - How is uncertainty or probability born? How to include current coinflips operand and operators to [[math]] mathematical science, probabliistic programming language에 포함연관시킬지에 - Is it $\subseteq$ or $\subsetneq$ for form and hyperreality? >Given sp(axiom) $\subsetneq$ system (Gödel's incompleteness theorem) > then sp(symbol) $\subsetneq$hyperreality? "Avatar's experience (interface, identity, rule, power) are all expresseed as the informatin of representation of the informamtion itself" means everything is expressed as symbols which form the basis for the world where is Avatar resides. This is similar to how axioms forms the basis of the system which is built upon. - [v] What is the difference between Axiom and Theorem? We assume Axiom to be true as we need to build up the tautology logic (Theorem) based on something. We don't define `Set` and `element` or `line, point, plane` and line `crosses` point. - hyperreality from the [ref1](https://khulib.tistory.com/984) on its relation on metabus,