Search Results for author:
Found 2 papers, 0 papers with code
Is the Number of Trainable Parameters All That Actually Matters?
Recent work has identified simple empirical scaling laws for language models, linking compute budget, dataset size, model size, and autoregressive modeling loss.
Deep Multi-Facial Patches Aggregation Network For Facial Expression Recognition
Results show that the proposed approach achieves state-of-art FER deep learning approaches performance when the model is trained and tested on images from the same dataset.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
