Certifiable Distributional Robustness with Principled Adversarial Training
- the best paper ICLR2018

https://openreview.net/forum?id=Hk6kPgZA-

The Random Network Distillation (RND) is a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity. No extrinsic reward is needed but the network will learn it by itself.

Tested across 50+ different games, it worked pretty well. Some of the agent learnt the game's objective even though the objective was not set through an extrinsic reward.

Article: https://lnkd.in/dUtf2JZ
Paper: https://lnkd.in/dRpZXu4
Code: https://lnkd.in/d5B__cE

BOOOOOM! See you all in Google HQ, Milan!

March 7th, 2019 | From 7.15 pm.

https://www.meetup.com/it-IT/Google-Cloud-Developer-Community-Milano/events/259120692/

⚡️ The best #AI of the week: #deeplearning, #computervision & #NLP free resources from across the internet in one place, every week. ⚡️

💡 Google | Face and Hand tracking in the browser with MediaPipe and TensorFlow: https://lnkd.in/dQRSB7U

💡 Berkeley | Speeding Up Transformer Training and Inference By Increasing Model Size: https://lnkd.in/dV5qZ4S

💡 CVPR-2020 | Zero-shot video classification by end-to-end training of 3D convolutional neural networks: https://lnkd.in/djs98Ew

💡 Google | Connecting Vision and Language with Localized Narratives: https://lnkd.in/dD6hjUq

More: https://www.linkedin.com/feed/update/urn:li:activity:6643790787312140288

⚡️ The best #AI of the week: #deeplearning, #computervision & #NLP free resources from across the internet in one place, every week. ⚡️

💡 MIT | How to make a pizza - Learning a compositional layer-based GAN model: https://lnkd.in/gFaVgnR

More: https://www.linkedin.com/feed/update/urn:li:activity:6645227487855022080

🔥🧨 Microsoft releases an #AI made by Convolutions + Transformers 🔥🧨


Code, paper and more: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6783020475627945984-F8rv

⭐⭐This #AI uses *MIRRORS* to largely improve the 3D human pose reconstruction⭐⭐


Code and paper: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-ugcPost-6783719931075723264-PE0z

🌎🌍🌏 An end-to-end #AI framework able to de-render the world's revolutionary artefacts 🌎🌍🌏

More: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6786307882448146432-uKsm

🏆🧢 Make VGG-style ConvNets Great Again 🧢🏆

Pretrained models, code for building the model, training, and the conversion from training-time model to inference-time: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6786931467214745601-hTc6

🙈 Removing tattoos with this #AI project 🙈

More: https://www.linkedin.com/posts/visionarynet_ai-fastai-pytorch-activity-6787791059402469376--bNq/