Associated with
Marcin Lewek
Posted Mar 3, 2021
•
7 min read
Word2vec: Loss Function
The difference between probabilistic output vectors and target vectors is crucial for the network to learn. How can you measure this difference? What does the learning process look like? How do we indicate when our model is smart enough?
More Ways to Read:
🧃
Summarize
--
The key takeaways that can be read in under a minute
Sign up to unlock
Worth the squeeze
Get access to the condensed version of this piece, and every other article on The Juice, and so much more.
Start a free account on The Juice and we'll send you weekly emails sharing which podcasts, blogs, guides,
etc. are trending with other marketing or sales pros. We call it the Top 5!
Other content from
edrone
