How to Measure FLOP/s for Neural Networks Empirically? – Epoch
Computing the utilization rate for multiple Neural Network architectures.
Algorithms, Free Full-Text
Neural Architecture Search: Learning How to Learn
NeurIPS 2023
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, Journal of Big Data
What can flatness teach us about why Neural Networks generalise?, by Chris Mingard
2022-4-24: Merging networks, Wall of MoE papers, Diverse models transfer better
Frontiers Backpropagation With Sparsity Regularization for Spiking Neural Network Learning
What a Compute-Centric Framework Says About Takeoff Speeds
How to measure FLOP/s for Neural Networks empirically? — LessWrong
The comparison between normalizing importances by FLOPs and memory.
How to Measure FLOP/s for Neural Networks Empirically? – Epoch