# on 10-May-2018 (Thu)

#### Flashcard 1729359645964

Tags
#Borges
Question
Lo que yo encuentro sobre todo malo en los deportes es la idea de que alguien [...] y de que alguien [...] , y de que este hecho suscite [...] .

status measured difficulty not learned 37% [default] 0
Borges, Jorge Luis sur Twitter : &quot;Lo que yo encuentro sobre todo malo en los deportes es la idea de que alguien gane y de que alguien pierda, y de que este hecho suscite riva… https://t.co/3bP06RPSjB&quot;
Unblock @BorgesJorgeL Report Tweet Add to other Moment Add to new Moment <span>Lo que yo encuentro sobre todo malo en los deportes es la idea de que alguien gane y de que alguien pierda, y de que este hecho suscite rivalidades. Translate from Spanish Translated from Spanish by Bing What I find especially bad at sports is the idea that someone wins an

#### Flashcard 1767207210252

Tags
Question
[...] can be used to simplify wording of items
Context cues

The tags in my system

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Context cues can be used to simplify wording of items

#### Original toplevel document

20 rules of formulating knowledge in learning
This is roughly equivalent to 25-fold saving in time in the period of 20 years ! Such examples are not rare! They are most effectively handled with the all the preceding rules targeted on simplicity and against the interference <span>Context cues simplify wording You can use categories in SuperMemo 2000/2002, provide different branches of knowledge with a different look (different template), use reference labels (Title, Author, Date, etc.

#### Flashcard 1803172580620

Tags
#french #verbs
Question
In present tense, verbs whose infinitive ends in -ir add [...] to the stem.
-is, -is, -it, -issons, -issez, -issent

finir: je finis; tu finis; il, elle, on finit; nous finissons; vous finissez; ils, elles finissent

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Verbs whose infinitive ends in -ir add -is, -is, -it, -issons, -issez, -issent to the stem. finir : je finis; tu finis; il, elle, on finit; nous finissons; vous finissez; ils, elles finissent

#### Original toplevel document (pdf)

cannot see any pdfs

#### Annotation 2961666608396

 #jardin-dhiver Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
Jardin d'hiver Lyrics Je voudrais du soleil vert Des dentelles et des théières Des photos de bord de mer Dans mon jardin d'hiver <span>Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre Je voudrais du

#### Annotation 2961668181260

 #jardin-dhiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
Je voudrais du soleil vert Des dentelles et des théières Des photos de bord de mer Dans mon jardin d'hiver Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver <span>Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre Je voudrais du Fred Astaire Revoir un Latécoère Je voudrais toujours te plaire Dans mon jardin d'hiver Je veux déjeuner par terre Comme au long des golfes clairs T'embrasser les yeux

#### Annotation 2961669754124

 #jardin-dhiver Je voudrais du Fred Astaire Revoir un Latécoère Je voudrais toujours te plaire Dans mon jardin d'hiver

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
ouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre <span>Je voudrais du Fred Astaire Revoir un Latécoère Je voudrais toujours te plaire Dans mon jardin d'hiver Je veux déjeuner par terre Comme au long des golfes clairs T'embrasser les yeux ouverts Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en

#### Annotation 2961671326988

 #jardin-dhiver Je veux déjeuner par terre Comme au long des golfes clairs T'embrasser les yeux ouverts Dans mon jardin d'hiver

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
e novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre Je voudrais du Fred Astaire Revoir un Latécoère Je voudrais toujours te plaire Dans mon jardin d'hiver <span>Je veux déjeuner par terre Comme au long des golfes clairs T'embrasser les yeux ouverts Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre

#### Flashcard 2961672899852

Tags
#jardin-dhiver
Question
Je voudrais [...]
Comme en Nouvelle-Angleterre
de la lumière

(Je veux changer d'atmosphère
Dans mon jardin d'hiver)

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver

#### Original toplevel document

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
Jardin d'hiver Lyrics Je voudrais du soleil vert Des dentelles et des théières Des photos de bord de mer Dans mon jardin d'hiver <span>Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre Je voudrais du

#### Flashcard 2961675259148

Tags
#jardin-dhiver
Question
Je voudrais de la lumière
[...]
Comme en Nouvelle-Angleterre

(Je veux changer d'atmosphère
Dans mon jardin d'hiver)

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver

#### Original toplevel document

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
Jardin d'hiver Lyrics Je voudrais du soleil vert Des dentelles et des théières Des photos de bord de mer Dans mon jardin d'hiver <span>Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre Je voudrais du

#### Flashcard 2961678404876

Tags
#jardin-dhiver
Question
Je voudrais de la lumière
Comme en Nouvelle-Angleterre
[...]
Dans mon jardin d'hiver
Je veux changer d'atmosphère

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver

#### Original toplevel document

Henri Salvador – Jardin d'hiver Lyrics | Genius Lyrics
Jardin d'hiver Lyrics Je voudrais du soleil vert Des dentelles et des théières Des photos de bord de mer Dans mon jardin d'hiver <span>Je voudrais de la lumière Comme en Nouvelle-Angleterre Je veux changer d'atmosphère Dans mon jardin d'hiver Ta robe à fleur Sous la pluie de novembre Mes mains qui courent Je n'en peux plus de t'attendre Les années passent Qu'il est loin l'âge tendre Nul ne peut nous entendre Je voudrais du

#### Annotation 2961684696332

 Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian.

\mathfrak{Michael Betancourt} sur Twitter : &quot;Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian.&quot;
Unblock @betanalpha Report Tweet Add to other Moment Add to new Moment <span>Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian. 10:20 PM - 5 Jan 2017 110 Retweets

#### Flashcard 2961687842060

Tags
#betancourt
Question
Remember that using Bayes' Theorem doesn't make you a Bayesian. [...] makes you a Bayesian.
Quantifying uncertainty with probability

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian.

#### Original toplevel document

\mathfrak{Michael Betancourt} sur Twitter : &quot;Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian.&quot;
Unblock @betanalpha Report Tweet Add to other Moment Add to new Moment <span>Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian. 10:20 PM - 5 Jan 2017 110 Retweets

#### Annotation 2961692822796

 #culture It’s more helpful to think about exploitation and disrespect than to define cultural “ownership”

The Question of Cultural Appropriation | Current Affairs
l Appropriation <span>It’s more helpful to think about exploitation and disrespect than to define cultural “ownership”… by Briahna Joy Gray The trouble with Elvis’s version of “Hound Dog” is not that i

#### Flashcard 2961694395660

Tags
#culture
Question
It’s more helpful to think about [...] than to define cultural “ownership”
exploitation and disrespect

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
It’s more helpful to think about exploitation and disrespect than to define cultural “ownership”

#### Original toplevel document

The Question of Cultural Appropriation | Current Affairs
l Appropriation <span>It’s more helpful to think about exploitation and disrespect than to define cultural “ownership”… by Briahna Joy Gray The trouble with Elvis’s version of “Hound Dog” is not that i

#### Flashcard 2961695968524

Tags
#culture
Question
It’s more helpful to think about exploitation and disrespect than to define [...]
cultural “ownership”

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
It’s more helpful to think about exploitation and disrespect than to define cultural “ownership”

#### Original toplevel document

The Question of Cultural Appropriation | Current Affairs
l Appropriation <span>It’s more helpful to think about exploitation and disrespect than to define cultural “ownership”… by Briahna Joy Gray The trouble with Elvis’s version of “Hound Dog” is not that i

#### Annotation 2961700162828

 #stan Currently, the stan repo includes the language, the algorithms, and the service API for the interfaces.

Home · stan-dev/stan Wiki · GitHub
math <- stan <- pystan <- rstan <- rstanarm <- cmdstan <- statastan <- matlabstan <- stan.jl <- MathematicaStan <span>Currently, the stan repo includes the language, the algorithms, and the service API for the interfaces. There are additional repos for tools such as the emacs mode, R plotting, R Shiny interface, web pages, etc. Developer Process Process Dev process overview Git process New Fu

#### Flashcard 2961701735692

Tags
#stan
Question
Currently, the stan repo includes [...].
the language, the algorithms, and the interfaces

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Currently, the stan repo includes the language, the algorithms, and the service API for the interfaces.

#### Original toplevel document

Home · stan-dev/stan Wiki · GitHub
math <- stan <- pystan <- rstan <- rstanarm <- cmdstan <- statastan <- matlabstan <- stan.jl <- MathematicaStan <span>Currently, the stan repo includes the language, the algorithms, and the service API for the interfaces. There are additional repos for tools such as the emacs mode, R plotting, R Shiny interface, web pages, etc. Developer Process Process Dev process overview Git process New Fu

#### Annotation 2961706716428

 #best-practice #stan Your model is only as good as your ability to communicate it to others, and communication is drastically improved by treating your Stan program as a piece of software and applying the best practices from the software development community.

Stan Best Practices · stan-dev/stan Wiki · GitHub
tistical practice is a lifelong endeavor that continuously evolves as we learn more, but below are a list of best practices that will help accelerate you along that evolution as quickly as possible. 1. Treat your Stan program as software <span>Your model is only as good as your ability to communicate it to others, and communication is drastically improved by treating your Stan program as a piece of software and applying the best practices from the software development community. This helps not only to promote reproducibility but also to facilitate prompt answers from the Stan community when you run into problems. Write your program to be easily read. Use in

#### Annotation 2961708289292

 #best-practice #stan Ideally, your analysis will be broken up into a Stan program, a data file, possibly an init file, and scripts that process the analysis in your favorite environment.

Stan Best Practices · stan-dev/stan Wiki · GitHub
so that anyone can fit your model in any of the Stan interfaces. Saving data and inits is simplified with the stan_rdump and read_rdump functions provided by some of the interfaces -- see the individual interfaces for more information. <span>Ideally, your analysis will be broken up into a Stan program, a data file, possibly an init file, and scripts that process the analysis in your favorite environment. Because each of these files will constantly evolve as you improve your analysis, we highly recommend using version control software such as git and supporting services like GitHub.

#### Annotation 2961709862156

 #best-practice #stan Data "corrections" such as background subtraction and deconvolution censor information in the data and limit how much you can learn in a given experiment

Stan Best Practices · stan-dev/stan Wiki · GitHub
ng parameters all the way to the measurement and, ultimately, the raw data. Reason about how the data were generated with the experts who collected the data, breaking the process up into sequential steps that can be modeled piece by piece. <span>Data "corrections" such as background subtraction and deconvolution censor information in the data and limit how much you can learn in a given experiment. On the other hand, modeling the data generatively as a sum of signal plus background or signal smeared with measurement variability allows you to build an accurate model capable to ex

#### Annotation 2961711435020

 #best-practice #stan modeling the data generatively as a sum of signal plus background or signal smeared with measurement variability allows you to build an accurate model capable to extracting as much information from the data as possible.

Stan Best Practices · stan-dev/stan Wiki · GitHub
to sequential steps that can be modeled piece by piece. Data "corrections" such as background subtraction and deconvolution censor information in the data and limit how much you can learn in a given experiment. On the other hand, <span>modeling the data generatively as a sum of signal plus background or signal smeared with measurement variability allows you to build an accurate model capable to extracting as much information from the data as possible. 3. Start simple As important as generative modeling is, it's also important to start simple. Instead of trying to model every detail of the experiment immediately, begin with a si

#### Annotation 2961713007884

 #best-practice #stan Instead of trying to model every detail of the experiment immediately, begin with a simple approximation that captures the gross features of the data generating process.

Stan Best Practices · stan-dev/stan Wiki · GitHub
smeared with measurement variability allows you to build an accurate model capable to extracting as much information from the data as possible. 3. Start simple As important as generative modeling is, it's also important to start simple. <span>Instead of trying to model every detail of the experiment immediately, begin with a simple approximation that captures the gross features of the data generating process. Relative to long, complex models, simple models are much easier to communicate and drastically easier to debug. Once you can fit the initial simple model you can add more structure

#### Annotation 2961714580748

 #best-practice #stan One of the most powerful means of validating a statistical algorithm is to verify that you can recover the ground truth from simulated data.

Stan Best Practices · stan-dev/stan Wiki · GitHub
m used in Stan. All of these criteria are necessary but not sufficient conditions for a good fit -- in other words they all identify problems that will ensure a bad fit but none of them can guarantee a good fit. Recover simulated values <span>One of the most powerful means of validating a statistical algorithm is to verify that you can recover the ground truth from simulated data. Begin by selecting reasonable "true" values for each of your parameters, simulating data according to your model, and then trying to fit your model with the simulated data.

#### Annotation 2961716153612

 #best-practice #stan A nice consistency check is whether or not the 5% to 95% marginal posterior interval captures each of the "true" parameter values.

Stan Best Practices · stan-dev/stan Wiki · GitHub
hat you can recover the ground truth from simulated data. Begin by selecting reasonable "true" values for each of your parameters, simulating data according to your model, and then trying to fit your model with the simulated data. <span>A nice consistency check is whether or not the 5% to 95% marginal posterior interval captures each of the "true" parameter values. If your fit does not pass this check then something is going wrong with the statistical algorithm and your model, and you will not be able to trust it when applied to real data. The

#### Annotation 2961717726476

 #best-practice #stan The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is the split R-hat statistic which quantifies the consistency of an ensemble of Markov chains.

Stan Best Practices · stan-dev/stan Wiki · GitHub
mputing environment like R or Python. The simulation process itself will follow directly from the model, although if you have not focused on building your model generatively then it may not be easy to see that! Check generic diagnostics <span>The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is the split R-hat statistic which quantifies the consistency of an ensemble of Markov chains. The idea is to run multiple Markov chains, 4 is an okay default but running more makes the diagnostic more sensitive, and ensure that they're all exploring the same regions of paramete

#### Annotation 2961719299340

 #best-practice #stan Slow chains lead to low numbers of effective samples, and if there are too few effective samples then we can't accurate estimate the number of effective samples at all.

Stan Best Practices · stan-dev/stan Wiki · GitHub
he others then all of the chains are suspect! In practice we have found that requiring Rhat < 1.1 is a good default requirement for each parameter. Another potential problem to keep in mind is Markov chains that explore very slowly. <span>Slow chains lead to low numbers of effective samples, and if there are too few effective samples then we can't accurate estimate the number of effective samples at all. A good check for such issues is the number of effective samples per iteration -- if N_eff / N < 0.001 then you should be suspect of the effective sample size calculation. Check

#### Annotation 2961720872204

 #best-practice #stan The Folk Theorem of Statistical Computing is a heuristic developed by Andrew Gelman stating that most statistical computational problems are due not to the algorithm being used but rather the model itself.

Stan Best Practices · stan-dev/stan Wiki · GitHub
in some interfaces, namely RStan, but they can be directly access in the fit output in all interfaces. There is an additional energy diagnostic in development that will be made available to the interfaces soon. 5. Heed the Folk Theorem <span>The Folk Theorem of Statistical Computing is a heuristic developed by Andrew Gelman stating that most statistical computational problems are due not to the algorithm being used but rather the model itself. For example, a poorly-identified model with diffuse priors will require sojourns into the extremes of parameter space that will break even the best statistical algorithms. Instead of

#### Annotation 2961722445068

 #best-practice #stan The Folk Theorem is an important perspective because if forces the user to confront and evaluate the assumptions inherent to their model.

Stan Best Practices · stan-dev/stan Wiki · GitHub
pace that will break even the best statistical algorithms. Instead of trying to build an algorithm that can handle such extreme values, we can simply replace the diffuse priors with weakly-informative priors and use the existing algorithm. <span>The Folk Theorem is an important perspective because if forces the user to confront and evaluate the assumptions inherent to their model. This is especially useful when adhering to a sequential model building process where problematic model structures are easy to identify. Moreover, the Folk Theorem provides continued m

#### Flashcard 2961724017932

Tags
#best-practice #stan
Question
[...] limit how much you can learn in a given experiment
Data "corrections"

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Data "corrections" such as background subtraction and deconvolution censor information in the data and limit how much you can learn in a given experiment

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
ng parameters all the way to the measurement and, ultimately, the raw data. Reason about how the data were generated with the experts who collected the data, breaking the process up into sequential steps that can be modeled piece by piece. <span>Data "corrections" such as background subtraction and deconvolution censor information in the data and limit how much you can learn in a given experiment. On the other hand, modeling the data generatively as a sum of signal plus background or signal smeared with measurement variability allows you to build an accurate model capable to ex

#### Flashcard 2961726377228

Tags
#best-practice #stan
Question
The Folk Theorem forces the user to [...] inherent to their model.
confront and evaluate the assumptions

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
The Folk Theorem is an important perspective because if forces the user to confront and evaluate the assumptions inherent to their model.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
pace that will break even the best statistical algorithms. Instead of trying to build an algorithm that can handle such extreme values, we can simply replace the diffuse priors with weakly-informative priors and use the existing algorithm. <span>The Folk Theorem is an important perspective because if forces the user to confront and evaluate the assumptions inherent to their model. This is especially useful when adhering to a sequential model building process where problematic model structures are easy to identify. Moreover, the Folk Theorem provides continued m

#### Flashcard 2961728736524

Tags
#best-practice #stan
Question

The Folk Theorem of Statistical Computing states that most statistical computational problems are due not to the algorithm being used but rather [...].

the model itself

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
ml> The Folk Theorem of Statistical Computing is a heuristic developed by Andrew Gelman stating that most statistical computational problems are due not to the algorithm being used but rather the model itself. <html>

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
in some interfaces, namely RStan, but they can be directly access in the fit output in all interfaces. There is an additional energy diagnostic in development that will be made available to the interfaces soon. 5. Heed the Folk Theorem <span>The Folk Theorem of Statistical Computing is a heuristic developed by Andrew Gelman stating that most statistical computational problems are due not to the algorithm being used but rather the model itself. For example, a poorly-identified model with diffuse priors will require sojourns into the extremes of parameter space that will break even the best statistical algorithms. Instead of

#### Flashcard 2961731095820

Tags
#best-practice #stan
Question

[...] states that most statistical computational problems are due not to the algorithm being used but rather the model itself.

The Folk Theorem

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
The Folk Theorem of Statistical Computing is a heuristic developed by Andrew Gelman stating that most statistical computational problems are due not to the algorithm being used but rather the model itse

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
in some interfaces, namely RStan, but they can be directly access in the fit output in all interfaces. There is an additional energy diagnostic in development that will be made available to the interfaces soon. 5. Heed the Folk Theorem <span>The Folk Theorem of Statistical Computing is a heuristic developed by Andrew Gelman stating that most statistical computational problems are due not to the algorithm being used but rather the model itself. For example, a poorly-identified model with diffuse priors will require sojourns into the extremes of parameter space that will break even the best statistical algorithms. Instead of

#### Flashcard 2961733455116

Tags
#best-practice #stan
Question
Slow chains lead to low numbers of [...]
effective samples

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Slow chains lead to low numbers of effective samples, and if there are too few effective samples then we can't accurate estimate the number of effective samples at all.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
he others then all of the chains are suspect! In practice we have found that requiring Rhat < 1.1 is a good default requirement for each parameter. Another potential problem to keep in mind is Markov chains that explore very slowly. <span>Slow chains lead to low numbers of effective samples, and if there are too few effective samples then we can't accurate estimate the number of effective samples at all. A good check for such issues is the number of effective samples per iteration -- if N_eff / N < 0.001 then you should be suspect of the effective sample size calculation. Check

#### Flashcard 2961735814412

Tags
#best-practice #stan
Question
[...] indicates that the algorithm is not exploring the posterior efficiently
Slow chains

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Slow chains lead to low numbers of effective samples, and if there are too few effective samples then we can't accurate estimate the number of effective samples at all.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
he others then all of the chains are suspect! In practice we have found that requiring Rhat < 1.1 is a good default requirement for each parameter. Another potential problem to keep in mind is Markov chains that explore very slowly. <span>Slow chains lead to low numbers of effective samples, and if there are too few effective samples then we can't accurate estimate the number of effective samples at all. A good check for such issues is the number of effective samples per iteration -- if N_eff / N < 0.001 then you should be suspect of the effective sample size calculation. Check

#### Flashcard 2961738173708

Tags
#best-practice #stan
Question
The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is [...]
the split R-hat statistic

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is the split R-hat statistic which quantifies the consistency of an ensemble of Markov chains.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
mputing environment like R or Python. The simulation process itself will follow directly from the model, although if you have not focused on building your model generatively then it may not be easy to see that! Check generic diagnostics <span>The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is the split R-hat statistic which quantifies the consistency of an ensemble of Markov chains. The idea is to run multiple Markov chains, 4 is an okay default but running more makes the diagnostic more sensitive, and ensure that they're all exploring the same regions of paramete

#### Flashcard 2961740533004

Tags
#best-practice #stan
Question
the split R-hat statistic quantifies the [...].
consistency of an ensemble of Markov chains

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is the split R-hat statistic which quantifies the consistency of an ensemble of Markov chains.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
mputing environment like R or Python. The simulation process itself will follow directly from the model, although if you have not focused on building your model generatively then it may not be easy to see that! Check generic diagnostics <span>The best generic diagnostic for the accuracy of a Markov chain Monte Carlo algorithm is the split R-hat statistic which quantifies the consistency of an ensemble of Markov chains. The idea is to run multiple Markov chains, 4 is an okay default but running more makes the diagnostic more sensitive, and ensure that they're all exploring the same regions of paramete

#### Flashcard 2961742892300

Tags
#best-practice #stan
Question
A nice consistency check is whether or not [...] captures each of the "true" parameter values.
the 5% to 95% marginal posterior interval

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
A nice consistency check is whether or not the 5% to 95% marginal posterior interval captures each of the "true" parameter values.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
hat you can recover the ground truth from simulated data. Begin by selecting reasonable "true" values for each of your parameters, simulating data according to your model, and then trying to fit your model with the simulated data. <span>A nice consistency check is whether or not the 5% to 95% marginal posterior interval captures each of the "true" parameter values. If your fit does not pass this check then something is going wrong with the statistical algorithm and your model, and you will not be able to trust it when applied to real data. The

#### Flashcard 2961744465164

Tags
#best-practice #stan
Question
One of the most powerful means of validating a statistical algorithm is to verify that you can [...].
recover the ground truth from simulated data

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
One of the most powerful means of validating a statistical algorithm is to verify that you can recover the ground truth from simulated data.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
m used in Stan. All of these criteria are necessary but not sufficient conditions for a good fit -- in other words they all identify problems that will ensure a bad fit but none of them can guarantee a good fit. Recover simulated values <span>One of the most powerful means of validating a statistical algorithm is to verify that you can recover the ground truth from simulated data. Begin by selecting reasonable "true" values for each of your parameters, simulating data according to your model, and then trying to fit your model with the simulated data.

#### Flashcard 2961746038028

Tags
#best-practice #stan
Question
Instead of trying to model every detail of the experiment immediately, begin with a simple approximation that captures [...].
the gross features of the data generating process

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Instead of trying to model every detail of the experiment immediately, begin with a simple approximation that captures the gross features of the data generating process.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
smeared with measurement variability allows you to build an accurate model capable to extracting as much information from the data as possible. 3. Start simple As important as generative modeling is, it's also important to start simple. <span>Instead of trying to model every detail of the experiment immediately, begin with a simple approximation that captures the gross features of the data generating process. Relative to long, complex models, simple models are much easier to communicate and drastically easier to debug. Once you can fit the initial simple model you can add more structure

#### Flashcard 2961747610892

Tags
#best-practice #stan
Question
modeling the data generatively as [...] allows you to build an accurate model capable to extracting as much information from the data as possible.
a sum of signal plus background

or signal smeared with measurement variability

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
modeling the data generatively as a sum of signal plus background or signal smeared with measurement variability allows you to build an accurate model capable to extracting as much information from the data as possible.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
to sequential steps that can be modeled piece by piece. Data "corrections" such as background subtraction and deconvolution censor information in the data and limit how much you can learn in a given experiment. On the other hand, <span>modeling the data generatively as a sum of signal plus background or signal smeared with measurement variability allows you to build an accurate model capable to extracting as much information from the data as possible. 3. Start simple As important as generative modeling is, it's also important to start simple. Instead of trying to model every detail of the experiment immediately, begin with a si

#### Flashcard 2961749970188

Tags
#best-practice #stan
Question
Ideally, your analysis will be broken up into a [...4 parts...].
Stan program, a data file, possibly an init file, and scripts that process the analysis in your favorite environment

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Ideally, your analysis will be broken up into a Stan program, a data file, possibly an init file, and scripts that process the analysis in your favorite environment.

#### Original toplevel document

Stan Best Practices · stan-dev/stan Wiki · GitHub
so that anyone can fit your model in any of the Stan interfaces. Saving data and inits is simplified with the stan_rdump and read_rdump functions provided by some of the interfaces -- see the individual interfaces for more information. <span>Ideally, your analysis will be broken up into a Stan program, a data file, possibly an init file, and scripts that process the analysis in your favorite environment. Because each of these files will constantly evolve as you improve your analysis, we highly recommend using version control software such as git and supporting services like GitHub.

#### Annotation 2961754950924

 #priors Some principles we don't like: invariance, Jeffreys, entropy

Prior Choice Recommendations · stan-dev/stan Wiki · GitHub
r closed forms or for Gibbs; we don't care about that Computational goal in Stan: reducing instability which can typically arise from bad geometry in the posterior, heavy tails that can cause Stan to adapt poorly and have heavy tails <span>Some principles we don't like: invariance, Jeffreys, entropy Weakly informative prior should contain enough information to regularize: the idea is that the prior rules out unreasonable parameter values but is not so strong as to rule out val

#### Flashcard 2961756523788

Tags
#priors
Question
Some principles we don't like: [...]
invariance, Jeffreys, entropy

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Some principles we don't like: invariance, Jeffreys, entropy

#### Original toplevel document

Prior Choice Recommendations · stan-dev/stan Wiki · GitHub
r closed forms or for Gibbs; we don't care about that Computational goal in Stan: reducing instability which can typically arise from bad geometry in the posterior, heavy tails that can cause Stan to adapt poorly and have heavy tails <span>Some principles we don't like: invariance, Jeffreys, entropy Weakly informative prior should contain enough information to regularize: the idea is that the prior rules out unreasonable parameter values but is not so strong as to rule out val

#### Flashcard 2961766747404

Tags
#Réflexe #myotatique
Question
Qu'est ce que le réflexe myotatique ou réflexe d'étirment ?
C'est la contraction d'un muscle déclenché par son étirement.

status measured difficulty not learned 37% [default] 0

#### Flashcard 2961768320268

Tags
#Réflexe #myotatique
Question
Donner deux exemples de réflexes myotatiques
Qu'est ce que cela provoque ?
Par exemple la percussion du tendon du muscles du quadriceps (réflexe rotulien) ou du triceps (réflexe achilléen).
Provoquent un étirement bref de ces muscles.

status measured difficulty not learned 37% [default] 0

#### Flashcard 2961770155276

Tags
#Réflexe #myotatique
Question
Comment est considéré cet étirement ?
Il est considéré comme un stimulus qui; par voie réflexe, déclenche la contraction de ce même muscle.

status measured difficulty not learned 37% [default] 0

#### Flashcard 2961771990284

Tags
#Réflexe #myotatique
Question
Que se passe-t-il lors d'un réflexe par percussion du tendon ?
la stimulation très brève déclenche une contraction, très brève elle aussi du muscle.

status measured difficulty not learned 37% [default] 0

#### Flashcard 2961773563148

Tags
#Réflexe #myotatique
Question
Que cherche-t-on à faire pendant un examen médical de routine ?

Que'est ce que cela apport au médecin ?
On cherhce l'aspect phasique du réflexe myotique (phasique, car entraînent un mouvement bref).

Il le renseigne sur le fonctionnement, état du système nerveux.

status measured difficulty not learned 37% [default] 0

#has-images

spinit();

www.7739.com

#### [太阳城集团]注册即送300元,可提款,澳门博彩第一品牌！

www.8827.com

• null

1、政府保护仿制，充当“推销员”
1970年印度总理英迪拉·甘地主导修订了的《专利法》规定，对食品、药品只授予工艺专利，不授予产品专利，这意味着印度放弃了对药品化合物的知识产权保护，

2、人力成本低，技术雄厚

1.收货人请填写病人姓名，手机号无所谓，因为一旦被扣可以凭处方，诊断书去海关拿药。只有极个别城市是没有人情的，大多数省份都是可以拿出来的，但请一次不要购买太多，有倒卖嫌疑
2，广西，福建，四川，江苏，山东（据说有个重要的会议在六月份），这几个地方是经常扣货的，广西，四川几乎见一个扣一个，

#### Annotation 2961794796812

 #PATH When you type any command at the prompt (say, python), the system has a well-defined sequence of places that it looks for the executable. This sequence is defined in a system variable called PATH, which the user can specify. To see your PATH, you can type echo $PATH. status not read Running Jupyter with multiple Python and IPython paths - Stack Overflow thon installs and finds packages How Jupyter knows what Python to use For the sake of completeness, I'll try to do a quick ELI5 on each of these, so you'll know how to solve this issue in the best way for you. 1. Unix/Linux/OSX$PATH <span>When you type any command at the prompt (say, python ), the system has a well-defined sequence of places that it looks for the executable. This sequence is defined in a system variable called PATH , which the user can specify. To see your PATH , you can type echo $PATH . The result is a list of directories on your computer, which will be searched in order for the desired executable. From your output above, I assume that it contains this:$ echo

#### Annotation 2961796893964

 #PATH The result is a list of directories on your computer, which will be searched in order for the desired executable.

Running Jupyter with multiple Python and IPython paths - Stack Overflow
mpt (say, python ), the system has a well-defined sequence of places that it looks for the executable. This sequence is defined in a system variable called PATH , which the user can specify. To see your PATH , you can type echo $PATH . <span>The result is a list of directories on your computer, which will be searched in order for the desired executable. From your output above, I assume that it contains this:$ echo $PATH /usr/bin/:/Library/Frameworks/Python.framework/Versions/3.5/bin/:/usr/local/bin/ In windows echo %path% P #### Annotation 2961798991116  #PATH When you run python and do something like import matplotlib, Python has to play a similar game to find the package you have in mind. Similar to $PATH in unix, Python has sys.path that specifies these

Running Jupyter with multiple Python and IPython paths - Stack Overflow

#### Annotation 2961803185420

 #PATH is the current directory. Also, unless you modify this (which you shouldn't do unless you know exactly what you're doing) you'll usually find something called site-packages in the path: this is the default place that Python puts packages when you install them using python setup.py install, or pip, or conda, or a similar means.

Running Jupyter with multiple Python and IPython paths - Stack Overflow

#### Annotation 2961807379724

 #PATH Well, first make sure your $PATH variable is doing what you want it to. You likely have a startup script called something like ~/.bash_profile or ~/.bashrc that sets this $PATH variable.

Running Jupyter with multiple Python and IPython paths - Stack Overflow
s that the packages you can import when running python are entirely separate from the packages you can import when running ipython or a Jupyter notebook: you're using two completely independent Python installations. So how to fix this? <span>Well, first make sure your $PATH variable is doing what you want it to. You likely have a startup script called something like ~/.bash_profile or ~/.bashrc that sets this$PATH variable. On Windows, you can modify the user specific environment variables. You can manually modify that if you want your system to search things in a different order. When you first install an

#### Annotation 2961809476876

 #PATH But in order for this to happen, Jupyter needs to know where to look for the associated executable: that is, it needs to know which path the python sits in. These paths are specified in jupyter's kernelspec, and it's possible for the user to adjust them to their desires.
know where to look for the associated executable: that is, it needs to know which path the python sits in. These paths are specified in jupyter's kernelspec , and it's possible for the user to adjust them to their desires. For example, <span>here's the list of kernels that I have on my system: $jupyter kernelspec list Available kernels: python2.7 /Users/jakevdp/.ipython/kernels/python2.7 python3.3 /Users/jakevdp/.ipython/kernels/python3.3 python3.4 /Users/jakevdp/.ipython/kernels/python3.4 python3.5 /Users/jakevdp/.ipython/kernels/python3.5 python2 /Users/jakevdp/Library/Jupyter/kernels/python2 python3 /Users/jakevdp/Library/Jupyter/kernels/python3 Each of these is a directory containing some metadata that specifies the kernel name, the path to the executable, and other relevant info. You can adjust kernels manually, editing the metadata inside the directories listed above. The command to install a kernel can change depending on the kernel. IPython relies on the i #### Annotation 2961813671180  #PATH IPython relies on the ipykernel package which contains a command to install a python kernel: for example $ python - m ipykernel install  It will create a kernelspec associated with the Python executable you use to run this command. You can then choose this kernel in the Jupyter notebook to run your code with that Python.
specifies the kernel name, the path to the executable, and other relevant info. You can adjust kernels manually, editing the metadata inside the directories listed above. The command to install a kernel can change depending on the kernel. <span>IPython relies on the ipykernel package which contains a command to install a python kernel: for example $python -m ipykernel install It will create a kernelspec associated with the Python executable you use to run this command. You can then choose this kernel in the Jupyter notebook to run your code with that Python. You can see other options that ipykernel provides using the help command:$ python -m ipykernel install --help usage: ipython-kernel-install [-h] [--user] [--name NAME]