kwrobel
Re:Single Headed Attention RNN
on Wednesday November 27, 2019 @01:04PM (#21650287)
I agree. Perplexities (probability of a text) can be compared using different tokenization after normalization.
Re:What I Learned from Working 32 Hours a Week
on Sunday January 06, 2019 @09:48AM (#18838563)
In some countries it is mandatory by law to have 14 days in one block per year.
Re:Deep learning beginner to expert: techniques from Fast.ai
on Wednesday August 01, 2018 @03:21PM (#17666019)
"As Jeremy Howard points out, even academic papers often use softmax for multi-class classification, and I too have already seen it used incorrectly in blogs and papers during my short time studying DL."
AFAIK softmax should be used with mutli-class classification and sigmoid can be used with mutli-label classification.
Re:I had to learn Python to pay my taxes
on Saturday April 07, 2018 @04:59PM (#16782944)
AFAIK in Europe you need to pay taxes only when you convert (sell) crypto currency to real currency.
The Benefits of Attention for Document Classification
Re:High Expectations for Low Precision at Cern
on Thursday July 13, 2017 @10:00AM (#14761271)
Also in NLP domain a precision reduction may be applied: https://arxiv.org/abs/1706.06363
Re:Scientists have detected a major change to the Earth’s oceans
on Sunday February 19, 2017 @10:16AM (#13680067)
Read the paper and convince yourself.
Re:FastText – Library for fast text representation and classification
on Thursday August 04, 2016 @03:48PM (#12227978)
Is it multi label text classification or only multi class?
Re:Bag of Tricks for Efficient Text Classification
on Saturday July 09, 2016 @03:45PM (#12062954)
How a sequence of words is feeded to non-recurrent network?
Re:TensorFlow Simplified Interface
on Sunday April 03, 2016 @02:50PM (#11417120)
How it can be compared to keras?
Re:Google Knowledge Graph Search API
on Sunday December 20, 2015 @06:59AM (#10766822)
Talking about Cyc ontology, we are working on automatic Wikipedia articles classification: http://cycloped.io/