Bibliography (8):

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

2. CLIP: Connecting Text and Images: We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the ‘zero-shot’ capabilities of GPT-2 and GPT-3

3. ALIGN: Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

4. Microsoft COCO: Common Objects in Context

5. CogView: Mastering Text-to-Image Generation via Transformers

6. Wikipedia Bibliography:

   1. Wu Dao  :

      https://en.wikipedia.org/wiki/Wu_Dao

   2. Xiaoice

   3. OpenAI