[ML News] ConvNeXt: Convolutions return | China regulates algorithms | Saliency cropping examined

#mlnews #convnext #mt3

Your update on what’s new in the Machine Learning world!

OUTLINE:
0:00 – Intro
0:15 – ConvNeXt: Return of the Convolutions
2:50 – Investigating Saliency Cropping Algorithms
9:40 – YourTTS: SOTA zero-shot Text-to-Speech
10:40 – MT3: Multi-Track Music Transcription
11:35 – China regulates addictive algorithms
13:00 – A collection of Deep Learning interview questions & solutions
13:35 – Helpful Things
16:05 – AlphaZero explained blog post
16:45 – Ru-DOLPH: HyperModal Text-to-Image-to-Text model
17:45 – Google AI 2021 Review

References:
ConvNeXt: Return of the Convolutions
https://arxiv.org/abs/2201.03545
https://github.com/facebookresearch/ConvNeXt

Investigating Saliency Cropping Algorithms
https://openaccess.thecvf.com/content/WACV2022/papers/Birhane_Auditing_Saliency_Cropping_Algorithms_WACV_2022_paper.pdf
https://vinayprabhu.github.io/Saliency_Image_Cropping/paper_html/main.html
https://vinayprabhu.medium.com/on-the-twitter-cropping-controversy-critique-clarifications-and-comments-7ac66154f687
https://vinayprabhu.github.io/Saliency_Image_Cropping/

YourTTS: SOTA zero-shot Text-to-Speech
https://github.com/coqui-ai/TTS?utm_source=pocket_mylist
https://arxiv.org/abs/2112.02418?utm_source=pocket_mylist
https://coqui.ai/?utm_source=pocket_mylist
https://coqui.ai/blog/tts/yourtts-zero-shot-text-synthesis-low-resource-languages

MT3: Multi-Track Music Transcription
https://arxiv.org/abs/2111.03017
https://github.com/magenta/mt3
https://huggingface.co/spaces/akhaliq/MT3

[R] MT3: Multi-Task Multitrack Music Transcription from MachineLearning

China regulates addictive algorithms

China issues new rules to regulate algorithms, targeting addiction, monopolies, and overspending


https://qz.com/2109618/china-reveals-new-algorithm-rules-to-weaken-platforms-control-of-users/

A collection of Deep Learning interview questions & solutions
https://arxiv.org/abs/2201.00650?utm_source=pocket_mylist
https://arxiv.org/pdf/2201.00650.pdf

Helpful Things
https://docs.deepchecks.com/en/stable/index.html
https://github.com/deepchecks/deepchecks
https://docs.deepchecks.com/en/stable/examples/guides/quickstart_in_5_minutes.html
https://www.dagshub.com/
https://www.dagshub.com/docs/index.html
https://www.dagshub.com/blog/launching-dagshub-2-0/
https://bayesiancomputationbook.com/welcome.html
https://mlcontests.com/
https://github.com/Yard1/ray-skorch
https://github.com/skorch-dev/skorch
https://www.rumbledb.org/?utm_source=pocket_mylist
https://github.com/DarshanDeshpande/jax-models
https://github.com/s3prl/s3prl

AlphaZero explained blog post
https://joshvarty.github.io/AlphaZero/?utm_source=pocket_mylist

Ru-DOLPH: HyperModal Text-to-Image-to-Text model
https://github.com/sberbank-ai/ru-dolph
https://colab.research.google.com/drive/1gmTDA13u709OXiAeXWGm7sPixRhEJCga?usp=sharing

Google AI 2021 Review
https://ai.googleblog.com/2022/01/google-research-themes-from-2021-and.html

Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191

If you want to support me, the best thing to do is to share out the content 🙂

If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

YouTube Source for this AI Video

AI video(s) you might be interested in …