MIT 2022 - TinyML EfficientML Course (Prof Song Han)


Created: =dateformat(this.file.ctime,"dd MMM yyyy, hh:mm a") | Modified: =dateformat(this.file.mtime,"dd MMM yyyy, hh:mm a") Tags: TinyML

Annotations


Quantization Dynamic Quantization Static Quantization

developed by google recently, increase the range of FP16, while reducing the precision.

allows for training weights to be of larger range, since the precision not as important

another good tradeoff between range and precision again

AI/ML research leading to alot of advances in number representation, such as in FP8 (floating point 8)

https://semiengineering.com/will-floating-point-8-solve-ai-ml-overhead/

FP8 Formats for Deep Learning https://arxiv.org/abs/2209.05433