The "Adversarial Attacks and Defences Competition" by the world's tech giants (@Google , @BaiduResearch, @Snapchat , @Microsoft, etc.) is official: https://arxiv.org/pdf/1804.00097.pdf

https://www.youtube.com/watch?v=szcw38Ahblo

#NeuralNetworks #DeepLearning #ArtificialIntelligence

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

See you all at #Voxxed conference!

https://twitter.com/argovision/status/1084444328334905344?s=19

Open Position | full-stack developer for ML,CV, AI | More: https://www.linkedin.com/feed/update/urn:li:activity:6491988838486020096/

#artificialIntelligence #computervision #machinelearning #ai #javascript #java #linux

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/

SOLD-OUT: https://www.linkedin.com/feed/update/urn:li:activity:6508270006403502081/

ML-kit + lecture about AI at Google Italia. All the stuff (slides, sources, demo, models): https://www.linkedin.com/feed/update/urn:li:activity:6509746451516661760

The second Italian release of a distributed #neuralnetwork aim at monitoring the occupancy status of parking lots within the large retail spaces. More: https://www.linkedin.com/feed/update/urn:li:activity:6518839581461356544

Open position in ARGO Vision: https://www.linkedin.com/feed/update/urn:li:activity:6546741808918077441

Leaving Milan to attend C1A0_expo in Genoa! Anyone there?

Ready for my talk about computer vision and neural evolution? Topic: object detection, semantic segmentation, unconventional adversarial attacks & neural parking.

More: https://www.linkedin.com/posts/argo-vision_artificialintelligence-deeplearning-smartparking-activity-6601033667391430657-NpN3

⚡️ 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

We are hiring!

https://www.linkedin.com/posts/argo-vision_java-python-scala-activity-6653183068901384192-zoNd

A lightweight video motion re-targeting approach that is capable of transferring motion in spite of structural and view-angle disparities between the source and the target.

Source code, Paper & more: https://www.linkedin.com/feed/update/urn:li:activity:6661281544608460800