244 - What are embedding layers in keras?

Code generated in the video can be downloaded from here:
https://github.com/bnsreenu/python_for_microscopists

Embedding layer...
Maps each value in the input array to a vector of a defined size.​
The weights in this layer are learned during the training process.​
Initialization is performed (just like other keras layers).​

One-hot encoding is inefficient as most indices are zero. (e.g., Text with 1000 words means most of the elements are 0) ​
Integer encoding does not reflect the relationship between words. ​
Embedding allows for the representation of similar words with similar encoding.​
Values are learned (trainable).​