chris/fastbook
1
0
Fork 0
mirror of https://github.com/fastai/fastbook.git synced 2025-04-05 10:20:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #90 from philtrade/master

Browse Source 
s/Is/It/
This commit is contained in:
Sylvain Gugger 2020-04-09 08:38:22 -04:00 committed by GitHub
commit 98ef7adc15
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
09_tabular.ipynb
View File

@ -152,7 +152,7 @@
"\n", "\n",
"In addition, it is also valuable in its own right that embeddings are continuous. It is valuable because models are better at understanding continuous variables. This is unsurprising considering models are built of many continuous parameter weights and continuous activation values, which are updated via gradient descent, a learning algorithm for finding the minimums of continuous functions.\n", "In addition, it is also valuable in its own right that embeddings are continuous. It is valuable because models are better at understanding continuous variables. This is unsurprising considering models are built of many continuous parameter weights and continuous activation values, which are updated via gradient descent, a learning algorithm for finding the minimums of continuous functions.\n",
"\n", "\n",
"Is is also valuable because we can combine our continuous embedding values with truly continuous input data in a straightforward manner: we just concatenate the variables, and feed the concatenation into our first dense layer. In other words, the raw categorical data is transformed by an embedding layer, before it interacts with the raw continuous input data. This is how fastai, and the entity embeddings paper, handle tabular models containing continuous and categorical variables.\n", "It is also valuable because we can combine our continuous embedding values with truly continuous input data in a straightforward manner: we just concatenate the variables, and feed the concatenation into our first dense layer. In other words, the raw categorical data is transformed by an embedding layer, before it interacts with the raw continuous input data. This is how fastai, and the entity embeddings paper, handle tabular models containing continuous and categorical variables.\n",
"\n", "\n",
"An example using this concatenation approach is how Google do their recommendations on Google Play, as they explained in their paper [Wide & Deep Learning for Recommender Systems](https://arxiv.org/abs/1606.07792), and as shown in this figure from their paper:" "An example using this concatenation approach is how Google do their recommendations on Google Play, as they explained in their paper [Wide & Deep Learning for Recommender Systems](https://arxiv.org/abs/1606.07792), and as shown in this figure from their paper:"
] ]