Bibliography (8):

1. Compressive Transformers for Long-Range Sequence Modeling

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

3. SCaNN: Accelerating Large-Scale Inference with Anisotropic Vector Quantization

4. Generating Sequences With Recurrent Neural Networks

5. Improving Neural Language Models with a Continuous Cache

6. Wikipedia Bibliography:

   1. Differentiable function

   2. k-nearest neighbors algorithm

   3. GitHub