https://in.mathworks.com/help/rtw/ref/learnablescompression.html
Learnables Compression - Compression type, specified as "none" or "bfloat16" - MATLAB
Perform learnables compression and generate C/C++ code using Brain Floating Point format (bfloat16).
compression typenonematlab
https://uk.mathworks.com/help/coder/ug/code-generation-LSTM-learnables-compression-in-bfloat16.html
Code Generation for Sequence-to-Sequence Classification with Learnables Compression - MATLAB &...
Generate code for LSTM network with learnables compression.
code generationsequenceclassificationcompressionmatlab