Oops, missed Reply all once again. Copying the message
Yes, the only need for such similarity learners is to use them in a
pipeline. It's especially convenient if one wants to do non-linear metric
learning using Kernel PCA trick. Then it'd be just another step in the
pipeline.
What do you mean
Something like this:
class SimilarityTransformer(TransformerMixin):
def fit(self, X, y):
self.X_ = X; return self
def transform(self, X):
return -euclidean_distances(X, self.X_)
On Thu, Mar 26, 2015 at 6:28 PM, Artem barmaley@gmail.com wrote:
Yes, the only need for
On Thu, Mar 26, 2015 at 5:49 PM, Artem barmaley@gmail.com wrote:
1. Right, forgot to add that parameter. Well, I can apply an RBF kernel to
get a similarity matrix from a distance matrix inside transform.
2. Usual transformer returns neither distance, nor similarity, but
transforms the
Hm, but similarity-based clustering works with inter-data similarities,
doesn't it? The result's shape would be like [n_samples_in_transform,
n_samples_in_train] which is not what we want.
On Thu, Mar 26, 2015 at 12:36 PM, Mathieu Blondel math...@mblondel.org
wrote:
Something like this:
class
- Spectral clustering use similarities rather than distances and needs
affinity=precomputed (otherwise, it assumes that X is [n_samples,
n_features])
- Instead of duplicating each class, you could create a generic transformer
that outputs a similarity / distance matrix from X.
M.
On Thu, Mar 26,
1. Right, forgot to add that parameter. Well, I can apply an RBF kernel to
get a similarity matrix from a distance matrix inside transform.
2. Usual transformer returns neither distance, nor similarity, but
transforms the input space so that usual Euclidean distance acts like the
learned
Hey Gael,
I am sorry that I missed this comment of yours -
1. The design of multiple metric support is important and would bring
an immense usability gain.
But it will also require a framework of its own. I would say that this is
to be considered in a second step.
Could you expand a little
Hi Matthias.
As far as I know, the main goal for TPE was to support tree-structured
parameter spaces. I am not sure we want to go there yet because of the
more complex API.
On non-tree structured spaces, I think TPE performed worse than SMAC and GP.
With regard to your code: There might be
,
Christof
On 20150326 16:08, Andreas Mueller wrote:
Hi Matthias.
As far as I know, the main goal for TPE was to support tree-structured
parameter spaces. I am not sure we want to go there yet because of the
more complex API.
On non-tree structured spaces, I think TPE performed worse than SMAC
and GP
Dear all,
I have updated the proposal
https://docs.google.com/document/d/1nnrAsEfkXpGRlc_PMEeuUUQ1ZcNMfy-7M-dZcIVp2lU/edit?usp=sharing
following your advices.
I have reduced the number of proposed algorithms and I have tried to
explain better why we need them and how we can implement them.
The
the current interface to make it easier
to optimize any learner?
Christof
On 20150326 20:02, Christof Angermueller wrote:
Hi Andy and others,
I revised my proposal
(https://docs.google.com/document/d/1bAWdiu6hZ6-FhSOlhgH-7x3weTluxRfouw9op9bHBxs/edit?usp=sharing)
and submitted it to melange
interface to make it easier to
optimize any learner?
Christof
On 20150326 20:02, Christof Angermueller wrote:
Hi Andy and others,
I revised my proposal
(https://docs.google.com/document/d/1bAWdiu6hZ6-FhSOlhgH-7x3weTluxRfouw9op9bHBxs/edit?usp=sharing)
and submitted it to melange. Can you have
about how to define parameters.
Thanks for you suggestions,
Christof
On 20150326 16:08, Andreas Mueller wrote:
Hi Matthias.
As far as I know, the main goal for TPE was to support tree-structured
parameter spaces. I am not sure we want to go there yet because of the
more complex API.
On non
, I can not tell you if I will use ParamSklearn to
define hyperparameters. Maybe I will come back to you when I think for
carefully about how to define parameters.
Thanks for you suggestions,
Christof
On 20150326 16:08, Andreas Mueller wrote:
Hi Matthias.
As far as I know, the main goal
Hi, Gaël and group
I really appreciate your comments. You are right. I'd better to stand on
the shoulders of giants rather than build all things from scratch. I went
through the 120+ comments on the very very initial PR #116 in 2011,
https://github.com/scikit-learn/scikit-learn/pull/116. It is
It would be nice to do something else instead of crash and burn, but for the
moment that's on the user.
I think that in recent Python versions segfault can be captured.
--
Dive into the World of Parallel Programming
Sorry for the late reply, my internet connection failed me. I've seen only
cross validation being the problem for semi-supervised learning, on the
issue tracker. Would someone else like to discuss about this?
So, should I scrap the self-taught learning algorithm from the proposal?
Also, I'm
Sorry, apparently I clicked reply and my previous message went to Mathieu
only. Repeat them here:
In case of vector y there's no other way, but to assume transitivity. Which
is not general enough, but should work in a classification setting. After
all, many of these methods are designed to aid
Dear Christof, dear scikit-learn team,
This is a great idea, I highly encourage your idea to integrate Bayesian
Optimization into scikit-learn since automatically configuring
scikit-learn is quite powerful. It was done by the three winning teams
of the first automated machine learning
19 matches
Mail list logo
