I recently came across this paper Green AI.

In the paper they discussed using floating point operation (FPO) count during testing and implementation of Neural Networks (NNs) to compare the efficiency of various NNs.

I would like to look at this topic more generally. Mostly from a forecasting perspective where naive, state space, and auto regressive models are used heavily.

I would like to know if there exists information on the FPOs to calculate these simple models and if this does not exist are there estimation techniques to get to a rough idea of this value.


I found computational complexity of various machine learning algorithms, but I did not find FLOPs.

Here is the link https://www.thekerneltrip.com/machine/learning/computational-complexity-learning-algorithms/


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.