AI Weekly Update - March 8th, 2021 (#27)!

1 Views
Nhạc Chill
Nhạc Chill
10 Mar 2021

Thank you for watching! Please Subscribe!

Content Links:
Multimodal neurons (OpenAI): https://openai.com/blog/multimodal-neurons/
Multimodal neurons (Distil): https://distill.pub/2021/multimodal-neurons/
DeepDream (Wikipedia): https://en.wikipedia.org/wiki/DeepDream
CLIP (OpenAI): https://openai.com/blog/clip/
CLIP (Keras Code Examples): https://keras.io/examples/nlp/nl_image_search/
OpenAI Microscope: https://microscope.openai.com/models
Yannic Kilcher's Explanation of Multimodal Neurons: https://www.youtube.com/watch?v=Z_kWZpgEZ7w&t=622s
Wikipedia-based Image-Text Pairs: https://arxiv.org/pdf/2103.01913.pdf
WIT Dataset (GitHub repo): https://github.com/google-research-datasets/wit
Self-supervised learning: the dark matter of intelligence: https://ai.facebook.com/blog/s....elf-supervised-learn
ImageGPT: https://openai.com/blog/image-gpt/
SEER (FB AI Blog Post): https://ai.facebook.com/blog/s....eer-the-start-of-a-m
SEER (Research Paper): https://arxiv.org/pdf/2103.019....88.pdf?fbclid=IwAR2c
SwAV: https://arxiv.org/pdf/2006.09882.pdf
RegNet: https://arxiv.org/pdf/2003.13678.pdf
Adaptive Consistency Regularization for Semi-Supervised Learning: https://arxiv.org/pdf/2103.02193.pdf
Do Transformer Modifications Transfer: https://arxiv.org/pdf/2102.11972.pdf
Long Range Arena: https://arxiv.org/pdf/2011.04006.pdf
Perceiver: General Perception with Iterative Attention: https://arxiv.org/pdf/2103.03206.pdf
Transformer in Transformer: https://arxiv.org/pdf/2103.00112.pdf
Vision Transformer: https://ai.googleblog.com/2020..../12/transformers-for
Generative Adversarial Transformers: https://arxiv.org/pdf/2103.01209.pdf
StyleGAN: https://arxiv.org/pdf/1812.04948.pdf
State-of-the-art Image Generative Models: https://arankomatsuzaki.wordpr....ess.com/2021/03/04/s
Ultra Data-Efficient GAN Training: https://arxiv.org/pdf/2103.00397.pdf
Training GANs with limited data: https://arxiv.org/pdf/2006.06676.pdf
Predicting Video with VQ-VAE: https://sites.google.com/view/....predicting-video-wit
VQ-VAE: https://arxiv.org/pdf/1711.00937.pdf
SEER (RL): https://arxiv.org/pdf/2103.02886.pdf
GenoML: https://genoml.com/
Data Aug with Neural Rendering: https://arxiv.org/pdf/2103.02852.pdf
Principles for Tackling Distribution Shift: https://www.youtube.com/watch?v=QKBh6TmvBaw

Chapters
0:00 Beginning
16:38 Multimodal Neurons
25:29 Wikipedia Dataset
27:25 The Dark Matter of Intelligence
34:48 SEER
39:26 Adaptive Consistency Regularization
41:04 Do Transformer Modifications Transfer?
45:08 Perceiver
47:18 Transformer in Transformer
49:30 Generative Adversarial Transformers
51:45 State-of-the-art Image Generative Models
52:46 Ultra-Data Efficient GANs
56:00 Predicting Video with VQ-VAE
1:00:23 Data Aug with Neural Rendering
1:01:22 Principles for Tackling Distribution Shift
1:04:09 GenoML
1:04:51 Thanks for Watching!

Show more

Up next



0 Comments Sort By

No comments found

Facebook Comments