Bibliography (5):
Vision Transformer: An Image is Worth 16ร16 Words: Transformers for Image Recognition at Scale
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
ImageNet Large Scale Visual Recognition Challenge
Wikipedia Bibliography:
Tensor Processing Unit ยง Fourth generation TPUโโ:
https://en.wikipedia.org/wiki/Tensor_Processing_Unit#Fourth_generation_TPU
Neural scaling lawโโ:
https://en.wikipedia.org/wiki/Neural_scaling_law