My experience also: similarity/dissimilarity pairs in and a mahalanobis
type matrix out.
- John
On Tue, Apr 23, 2013 at 12:59 AM, <
scikit-learn-general-requ...@lists.sourceforge.net> wrote:
> Send Scikit-learn-general mailing list submissions to
> scikit-learn-general@lists.sourceforge.net
>
> To subscribe or unsubscribe via the World Wide Web, visit
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
> or, via email, send a message with subject or body 'help' to
> scikit-learn-general-requ...@lists.sourceforge.net
>
> You can reach the person managing the list at
> scikit-learn-general-ow...@lists.sourceforge.net
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of Scikit-learn-general digest..."
>
>
> Today's Topics:
>
> 1. Re: Fwd: , Write a book on "Learning Scikit " for Packt
> Publishing (Robert Kern)
> 2. Re: Metric Learning Algorithms (John Collins) (Robert
> McGibbon) (John Collins)
> 3. Re: Metric Learning Algorithms (Mathieu Blondel)
> 4. Re: Metric Learning Algorithms (Kenneth C. Arnold)
> 5. Re: Metric Learning Algorithms (Robert McGibbon)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Mon, 22 Apr 2013 22:53:18 +0530
> From: Robert Kern <robert.k...@gmail.com>
> Subject: Re: [Scikit-learn-general] Fwd: , Write a book on "Learning
> Scikit " for Packt Publishing
> To: scikit-learn-general@lists.sourceforge.net, Pritesh Dsouza
> <prite...@packtpub.com>
> Message-ID:
> <
> caf6fjiv_6d+xno8u4d7u+ccegqynvkigrw43cjrtegushuw...@mail.gmail.com>
> Content-Type: text/plain; charset=UTF-8
>
> On Mon, Apr 22, 2013 at 4:02 PM, Pritesh Dsouza <prite...@packtpub.com>
> wrote:
> > Hi Guys,
> >
> > I am Pritesh D'souza, an Author Relations Executive with Packt
> Publishing.
> > We publish computer-related books on a wide variety of IT topics.
> >
> > We have a new book project, Learning SciKit and we are looking for
> skilled
> > authors with the right expertise. When I came across this blog profile
> and I
> > thought it would be great to have you'll as authors for this book. Your
> > expertise in the subject is impressive and having you as our author
> would be
> > a pleasure.
>
> The name of the project is "scikit-learn", not "SciKit". "SciKit" is a
> general term for a number of different projects in the SciPy
> ecosystem.
>
> http://scikits.appspot.com/
>
> The term is similar in scope to the MATLAB(TM) "Toolbox" term. You
> would not title a book about the MATLAB(TM) Signal Processing
> Toolbox(TM) _Learning Toolbox_.
>
> Good luck in your search.
>
> --
> Robert Kern
>
>
>
> ------------------------------
>
> Message: 2
> Date: Mon, 22 Apr 2013 12:37:37 -0700
> From: John Collins <johnsso...@gmail.com>
> Subject: Re: [Scikit-learn-general] Metric Learning Algorithms (John
> Collins) (Robert McGibbon)
> To: scikit-learn-general@lists.sourceforge.net
> Message-ID:
> <
> caa7aakyhhowsmuuxdc7maopmao+1b0yj-yyqkh5dxbyhvna...@mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> It seems like there is already a manifold learning project in progress.
>
> These two topics are closely related.
> http://www.cs.cmu.edu/~liuy/lle_isomap_metric.pdf
> -------------- next part --------------
> An HTML attachment was scrubbed...
>
> ------------------------------
>
> Message: 3
> Date: Tue, 23 Apr 2013 09:41:57 +0900
> From: Mathieu Blondel <math...@mblondel.org>
> Subject: Re: [Scikit-learn-general] Metric Learning Algorithms
> To: scikit-learn-general@lists.sourceforge.net
> Message-ID:
> <
> caoksrly_bafhrm+qynamxu8pjquixwuxf9-2l+e+3w2co8g...@mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> On Mon, Apr 22, 2013 at 3:56 PM, Alexandre Gramfort <
> alexandre.gramf...@inria.fr> wrote:
>
> > > If people were interested in putting together a separate package in the
> > > style of the scikit collecting metric learning algorithms with a common
> > API,
> > > I would love to contribute to that too.
> >
>
> I'm also interested in metric learning but as others said we need to come
> up with a good API. For example, how would use expose the learned metric,
> say to reuse it in a k-NN? Since several people mentioned that they have
> code, it would be helpful to put it in a gist so we can come up with a
> unified API.
>
> Mathieu
> -------------- next part --------------
> An HTML attachment was scrubbed...
>
> ------------------------------
>
> Message: 4
> Date: Mon, 22 Apr 2013 20:56:55 -0400
> From: "Kenneth C. Arnold" <kcarn...@seas.harvard.edu>
> Subject: Re: [Scikit-learn-general] Metric Learning Algorithms
> To: Mathieu Blondel <math...@mblondel.org>,
> scikit-learn-general@lists.sourceforge.net
> Message-ID:
> <
> cafxoeyjyhvjppozl-4bank9ambgsfrbha-yrjqvx47lgscu...@mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
> Some gists:
>
> https://gist.github.com/kcarnold/5439917
> https://gist.github.com/kcarnold/5439945
>
> They are rather terribly documented, sorry.
>
> Input to such algorithms is usually given as:
> - a set of similarity and dissimilarity links,
> - relative comparisons (x is closer to y than w is to z), or
> - target distances (x should be no farther than q from y).
>
> The outputs of all methods I've worked with are Mahalanobis distances.
>
>
> -Ken
>
>
> On Mon, Apr 22, 2013 at 8:41 PM, Mathieu Blondel <math...@mblondel.org
> >wrote:
>
> >
> > On Mon, Apr 22, 2013 at 3:56 PM, Alexandre Gramfort <
> > alexandre.gramf...@inria.fr> wrote:
> >
> >> > If people were interested in putting together a separate package in
> the
> >> > style of the scikit collecting metric learning algorithms with a
> common
> >> API,
> >> > I would love to contribute to that too.
> >>
> >
> > I'm also interested in metric learning but as others said we need to come
> > up with a good API. For example, how would use expose the learned metric,
> > say to reuse it in a k-NN? Since several people mentioned that they have
> > code, it would be helpful to put it in a gist so we can come up with a
> > unified API.
> >
> > Mathieu
> >
> >
> >
> ------------------------------------------------------------------------------
> > Precog is a next-generation analytics platform capable of advanced
> > analytics on semi-structured data. The platform includes APIs for
> building
> > apps and a phenomenal toolset for data science. Developers can use
> > our toolset for easy data analysis & visualization. Get a free account!
> > http://www2.precog.com/precogplatform/slashdotnewsletter
> > _______________________________________________
> > Scikit-learn-general mailing list
> > Scikit-learn-general@lists.sourceforge.net
> > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
> >
> >
> -------------- next part --------------
> An HTML attachment was scrubbed...
>
> ------------------------------
>
> Message: 5
> Date: Tue, 23 Apr 2013 00:59:02 -0700
> From: Robert McGibbon <rmcgi...@gmail.com>
> Subject: Re: [Scikit-learn-general] Metric Learning Algorithms
> To: scikit-learn-general@lists.sourceforge.net
> Message-ID: <c945eca6-889a-44a8-b6ee-551d1f0f8...@gmail.com>
> Content-Type: text/plain; charset="us-ascii"
>
> > Input to such algorithms is usually given as:
> > - a set of similarity and dissimilarity links,
> > - relative comparisons (x is closer to y than w is to z), or
> > - target distances (x should be no farther than q from y).
> >
> > The outputs of all methods I've worked with are Mahalanobis distanc
>
> This is also consistent with my experience.
>
> -Robert
>
>
> On Apr 22, 2013, at 5:56 PM, Kenneth C. Arnold wrote:
>
> > Some gists:
> >
> > https://gist.github.com/kcarnold/5439917
> > https://gist.github.com/kcarnold/5439945
> >
> > They are rather terribly documented, sorry.
> >
> > Input to such algorithms is usually given as:
> > - a set of similarity and dissimilarity links,
> > - relative comparisons (x is closer to y than w is to z), or
> > - target distances (x should be no farther than q from y).
> >
> > The outputs of all methods I've worked with are Mahalanobis distances.
> >
> >
> > -Ken
> >
> >
> > On Mon, Apr 22, 2013 at 8:41 PM, Mathieu Blondel <math...@mblondel.org>
> wrote:
> >
> > On Mon, Apr 22, 2013 at 3:56 PM, Alexandre Gramfort <
> alexandre.gramf...@inria.fr> wrote:
> > > If people were interested in putting together a separate package in the
> > > style of the scikit collecting metric learning algorithms with a
> common API,
> > > I would love to contribute to that too.
> >
> > I'm also interested in metric learning but as others said we need to
> come up with a good API. For example, how would use expose the learned
> metric, say to reuse it in a k-NN? Since several people mentioned that they
> have code, it would be helpful to put it in a gist so we can come up with a
> unified API.
> >
> > Mathieu
> >
> >
> ------------------------------------------------------------------------------
> > Precog is a next-generation analytics platform capable of advanced
> > analytics on semi-structured data. The platform includes APIs for
> building
> > apps and a phenomenal toolset for data science. Developers can use
> > our toolset for easy data analysis & visualization. Get a free account!
> > http://www2.precog.com/precogplatform/slashdotnewsletter
> > _______________________________________________
> > Scikit-learn-general mailing list
> > Scikit-learn-general@lists.sourceforge.net
> > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
> >
> >
> >
> ------------------------------------------------------------------------------
> > Precog is a next-generation analytics platform capable of advanced
> > analytics on semi-structured data. The platform includes APIs for
> building
> > apps and a phenomenal toolset for data science. Developers can use
> > our toolset for easy data analysis & visualization. Get a free account!
> >
> http://www2.precog.com/precogplatform/slashdotnewsletter_______________________________________________
> > Scikit-learn-general mailing list
> > Scikit-learn-general@lists.sourceforge.net
> > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
> -------------- next part --------------
> An HTML attachment was scrubbed...
>
> ------------------------------
>
>
> ------------------------------------------------------------------------------
> Try New Relic Now & We'll Send You this Cool Shirt
> New Relic is the only SaaS-based application performance monitoring service
> that delivers powerful full stack analytics. Optimize and monitor your
> browser, app, & servers with just a few lines of code. Try New Relic
> and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_apr
>
> ------------------------------
>
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
> End of Scikit-learn-general Digest, Vol 39, Issue 45
> ****************************************************
>
------------------------------------------------------------------------------
Try New Relic Now & We'll Send You this Cool Shirt
New Relic is the only SaaS-based application performance monitoring service
that delivers powerful full stack analytics. Optimize and monitor your
browser, app, & servers with just a few lines of code. Try New Relic
and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_apr
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
