scottyli
Joined 13 years ago
Karma
59
Submissions
4
Member since
Feb 24
scottyli.com
View on Hacker NewsRecent submissions
Comment · 9 years ago
What are the downsides of transfer learning? How can it fail?
And do you just arbitrarily select the "cut off output layer" for the pretrained model when retraining with your own data on new layers?
Comment · 11 years ago
pg's essay on "How to disagree" (http://www.paulgraham.com/disagree.html) also serves as a useful guideline.
grep 'u r a fag' | rm;
Comment · 13 years ago
Original quote from Arnold Rothstein (Boardwalk Empire)