Bibliography (8):

1. SMYRF: Efficient Attention using Asymmetric Clustering

2. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

3. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

4. A domain-specific supercomputer for training deep neural networks

5. Large Scale GAN Training for High Fidelity Natural Image Synthesis

6. A Style-Based Generator Architecture for Generative Adversarial Networks

7. Wikipedia Bibliography:

   1. Locality-sensitive hashing

   2. Generative adversarial network