Y
Hacker News
new
|
ask
|
show
|
jobs
by
cubefox
124 days ago
It seems unlikely "model" was ever equivalent in meaning to "architecture". Otherwise there would be just one "CNN model" or just one "transformer model" insofar there is a single architecture involved.
1 comments
ruszki
124 days ago
First of all, hyperparameters. Second, organization, or connections. 3rd, cost function. 4th, activation function. 5th type of learning. Etc.
These are not weights. These were parts of models.
link
These are not weights. These were parts of models.