Deep Learning is cheap Solomonoff induction?
1 hour ago
April 11, 2011
Subscribe to:
Post Comments (Atom)
Popular Posts
- Alec Radford's animations for optimization algorithms
- Bilmiyorum diyebilmek
- 1. Ulusal Yapay Zeka Buluşması, Kapadokya
- Turkish Language Resources
- Courses
- Machine learning in 10 pictures
- Introducing Knet8: beginning deep learning with 100 lines of Julia
- Keynote, XVIII. Swiss-Turkish Economic Forum
- Emacs Turkish mode
- Singular Value Decomposition Notes
My Blog List
-
-
-
-
Podcasts!2 days ago
-
George B. Field, 1929-20244 months ago
-
Self-driving as a case study for AGI10 months ago
-
Sparks of Stupidity1 year ago
-
Reflections on ‘The Bitter Lesson’3 years ago
-
-
Commutative Diagrams Explained5 years ago
3 comments:
Can we use This tool for punctuation modeling in turkish?
thx in advance...
when applying a LM model, the default lm is evaluated as a back-off model. But how can a user tell "ngram -ppl" that the LM should be evaluated as interpolated model?
The srilm manual has cases for interpolation over multiple LMs, but how to specify interpolation for a single LM that is trained with "ngram-count -interpolate"?
thanks
Post a Comment