Hi there,
I looked into WordNGramAnalyzer in feature_extraction/text.py.
It occured to me that in case of nGram n>1, 'handle token n-grams' happends
before 'handle stop words', as shown in following snippet:
# handle token n-grams
if self.min_n != 1 or self.max_n != 1:
- Ursprüngliche Mail -
Von: "Peter Prettenhofer"
An: scikit-learn-general@lists.sourceforge.net
Gesendet: Dienstag, 22. November 2011 13:44:25
Betreff: Re: [Scikit-learn-general] SGD learning rate heuristic
2011/11/22 Andreas Müller :
> Hi Peter.
> Thanks for the quick answer.
>
>
> On
2011/11/22 Andreas Müller :
> Hi Peter.
> Thanks for the quick answer.
>
>
> On 11/22/2011 12:33 PM, Peter Prettenhofer wrote:
>> Hi Andy,
>>
>> I adopted the heuristic from Leon Bottou's sgd implementation (version
>> 1.3). He explains the heuristic in [1] - search for "Choosing the Gain
>> Schedu
Hi Peter.
Thanks for the quick answer.
On 11/22/2011 12:33 PM, Peter Prettenhofer wrote:
> Hi Andy,
>
> I adopted the heuristic from Leon Bottou's sgd implementation (version
> 1.3). He explains the heuristic in [1] - search for "Choosing the Gain
> Schedule". I'm not aware of any paper which des
Hi Andy,
I adopted the heuristic from Leon Bottou's sgd implementation (version
1.3). He explains the heuristic in [1] - search for "Choosing the Gain
Schedule". I'm not aware of any paper which describes the rational in
more depth.
Here's the quote from the slide: "Choose t_0 to make sure that t
Hi everybody.
Could someone please explain to me the learning rate heuristic in SGD?
Why is \eta_0 initialized the way it is?
Peter Prettenhofer mentioned it is taken from Leon Bottou's
sgd code. I found it there but no further explanation.
Is it explained in any of the papers? I could not find it.
