Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
courses:rg:2011-report-baby-steps [2011/10/26 14:46] kruza |
courses:rg:2011-report-baby-steps [2011/10/26 14:49] kruza |
||
---|---|---|---|
Line 3: | Line 3: | ||
Report by Oldřich Krůza//\\ | Report by Oldřich Krůza//\\ | ||
- | ===== Introduction | + | ==== Introduction ==== |
On Monday, October 24th 2011, we heard a talk about a paper by Valentin | On Monday, October 24th 2011, we heard a talk about a paper by Valentin | ||
Line 41: | Line 41: | ||
progressed from short sentences to longer, and identified the threshold, where | progressed from short sentences to longer, and identified the threshold, where | ||
it's best to start ignoring any more training data, at sentences of length 15. | it's best to start ignoring any more training data, at sentences of length 15. | ||
- | However, | + | However, |
If the model was to be fully unsupervised, | If the model was to be fully unsupervised, | ||
this threshold, because it cannot be safely assumed that it would be the same | this threshold, because it cannot be safely assumed that it would be the same | ||
Line 51: | Line 51: | ||
never seen before. | never seen before. | ||
- | === Conclusion === | + | ==== Conclusion |
All in all, it was a paper worth reading, well presented, and thoroughly | All in all, it was a paper worth reading, well presented, and thoroughly | ||
discussed, bringing useful general ideas as well as interesting details. | discussed, bringing useful general ideas as well as interesting details. |