diff --git a/_site/posts/post-with-code/image.jpg b/_site/posts/post-with-code/image.jpg deleted file mode 100644 index 3ec04c8..0000000 Binary files a/_site/posts/post-with-code/image.jpg and /dev/null differ diff --git a/_site/posts/post-with-code/index.html b/_site/posts/post-with-code/index.html deleted file mode 100644 index 4411a80..0000000 --- a/_site/posts/post-with-code/index.html +++ /dev/null @@ -1,466 +0,0 @@ - - - - - - - - - - - -Christopher Lennan - Embeddings primer - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-
- -
- -
-
-
-

Embeddings primer

-
-
embeddings
-
-
-
- - -
- -
-
Author
-
-

Christopher Lennan

-
-
- -
-
Published
-
-

November 8, 2023

-
-
- - -
- - -
- - - - -
- - - - -

-
-

Motivation

-

Embeddings have never been more en vogue - they are the core of Multimodal AI that fuses together the vision, speech, and text domains. The most prominent example is probably the recent OpenAI announcement that ChatGPT can now see, hear, and speak.

-

An embedding is a compressed, dense representation of the raw data, be it text, images, or sound. This is in contrast to a sparse vector representation like, e.g., TF-IDF for text data. Dense embeddings are usually not beyond 2k dimensions, whereas sparse embeddings tend to be much higher dimensional. Dense embeddings thus offer a more efficient downstream processing.

-
-
-
- -
-
-
-

Figure: MNIST 3D

-
- - -
- -
- -
- - - - \ No newline at end of file