EfficientML.ai Lecture 5 - Quantization Part I (MIT 6.5940, Fall 2024)

Transcript

okay welcome everybody let's get started with lecture five of efficient ml. so today we are going to jump into a new chapter about quantization so last lecture we learned about coing to reduce the number of parameters in a new network if you think about the total size of a model of a neural network model that equal to the number of parameters times... Read More