All the talks (invited and contributed) of ICML Conference
workshop on "Self-supervision in Audio and Speech" are now publicly available here
https://slideslive.com/icml-2020/selfsupervision-in-audio-and-speech
  
  workshop on "Self-supervision in Audio and Speech" are now publicly available here
https://slideslive.com/icml-2020/selfsupervision-in-audio-and-speech
SlidesLive
  
  ICML 2020 |
  The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning.
ICML is globally renowned for presenting and publishing cutting…
  ICML is globally renowned for presenting and publishing cutting…
We are pleased to share the conferences of the Neural Backpropagation Workshop that took place at Mila in December 2019. Talks by Yoshua Bengio, Irina Rish, Blake Richards and Gaël Varoquaux.
https://www.youtube.com/playlist?list=PLvSH07QabjqbUt-YrQaVgXeUpUteOEfiW
  
  https://www.youtube.com/playlist?list=PLvSH07QabjqbUt-YrQaVgXeUpUteOEfiW
YouTube
  
  Backpropagation Workshop 2019 - YouTube
  
  Analyses of Deep Learning (STATS 385)
Stanford University, Fall 2019 : https://stats385.github.io/lecture_videos
#ArtificialIntelligence #DeepLearning #MachineLearning
  Stanford University, Fall 2019 : https://stats385.github.io/lecture_videos
#ArtificialIntelligence #DeepLearning #MachineLearning
Neural Voice Puppetry: Audio-driven Facial Reenactment
paper https://arxiv.org/pdf/1912.05566.pdf
video https://www.youtube.com/watch?v=s74_yQiJMXA&feature=youtu.be
Github https://justusthies.github.io/posts/neural-voice-puppetry/
  
  paper https://arxiv.org/pdf/1912.05566.pdf
video https://www.youtube.com/watch?v=s74_yQiJMXA&feature=youtu.be
Github https://justusthies.github.io/posts/neural-voice-puppetry/
YouTube
  
  Neural Voice Puppetry: Audio-driven Facial Reenactment (ECCV 2020)
  Paper: https://arxiv.org/pdf/1912.05566v1.pdf
Online Demo: https://kaldir.vc.in.tum.de/neural_voice_puppetry
Project: https://justusthies.github.io/posts/neural-voice-puppetry/
We present Neural Voice Puppetry, a novel approach for audio-driven facial video…
  Online Demo: https://kaldir.vc.in.tum.de/neural_voice_puppetry
Project: https://justusthies.github.io/posts/neural-voice-puppetry/
We present Neural Voice Puppetry, a novel approach for audio-driven facial video…
List of Open-Source RL Algorithms
By Sergey Kolesnikov, https://docs.google.com/spreadsheets/d/1EeFPd-XIQ3mq_9snTlAZSsFY7Hbnmd7P5bbT8LPuMn0/edit#gid=0
#DeepLearning #MachineLearning #ReinforcementLearning
  
  By Sergey Kolesnikov, https://docs.google.com/spreadsheets/d/1EeFPd-XIQ3mq_9snTlAZSsFY7Hbnmd7P5bbT8LPuMn0/edit#gid=0
#DeepLearning #MachineLearning #ReinforcementLearning
Google Docs
  
  Open-source RL
  
  The Deep Learning Lecture Series
A collaboration between DeepMind and the UCL Centre for Artificial Intelligence : https://www.youtube.com/playlist?list=PLqYmG7hTraZCDxZ44o4p3N5Anz3lLRVZF
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
  
  A collaboration between DeepMind and the UCL Centre for Artificial Intelligence : https://www.youtube.com/playlist?list=PLqYmG7hTraZCDxZ44o4p3N5Anz3lLRVZF
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
YouTube
  
  DeepMind x UCL | Deep Learning Lecture Series 2020
  The Deep Learning Lecture Series is a collaboration between DeepMind and the UCL Centre for Artificial Intelligence. Over the past decade, Deep Learning has ...
  We’re excited to announce that our Generative Adversarial Networks Specialization will launch on September 30! 
Sign-up to be notified of upcoming course launches: https://hubs.ly/H0vLtPB0
  Sign-up to be notified of upcoming course launches: https://hubs.ly/H0vLtPB0
Transformer Reinforcement Learning
Leandro von Werra, GitHub : https://github.com/lvwerra/trl
#ProximalPolicyOptimization #Transformer #ReinforcementLearning
  
  Leandro von Werra, GitHub : https://github.com/lvwerra/trl
#ProximalPolicyOptimization #Transformer #ReinforcementLearning
GitHub
  
  GitHub - huggingface/trl: Train transformer language models with reinforcement learning.
  Train transformer language models with reinforcement learning. - huggingface/trl
  The Sparse Future of Deep Learning
Could this be the next quantum leap in AI research?
https://towardsdatascience.com/the-sparse-future-of-deep-learning-bce05e8e094a
  
  Could this be the next quantum leap in AI research?
https://towardsdatascience.com/the-sparse-future-of-deep-learning-bce05e8e094a
Medium
  
  The Sparse Future of Deep Learning
  Could this be the next quantum leap in AI research?
  Can Single Neurons Solve MNIST? The Computational Power of Biological Dendritic Trees
Ilenna Simone Jones, Konrad Paul Kording : https://arxiv.org/abs/2009.01269
#Neurons #DeepLearning #Cognition
  Ilenna Simone Jones, Konrad Paul Kording : https://arxiv.org/abs/2009.01269
#Neurons #DeepLearning #Cognition
ConvNets helping the visually impaired.
Wearable AI devices are going to become ubiquitous over the next decade.
I met the OrCam folks when they were just starting.
They've made a lot of progress in low-power ConvNet chips.
OrCam was founded by Amnon Shashua who also founded MobilEye (now part of Intel).
https://m.youtube.com/watch?feature=youtu.be&v=82oAUwwwG2Q
Post by yan lecun
  
  Wearable AI devices are going to become ubiquitous over the next decade.
I met the OrCam folks when they were just starting.
They've made a lot of progress in low-power ConvNet chips.
OrCam was founded by Amnon Shashua who also founded MobilEye (now part of Intel).
https://m.youtube.com/watch?feature=youtu.be&v=82oAUwwwG2Q
Post by yan lecun
YouTube
  
  OrCam and Messi are Empowering the Blind Community
  Watch the magical moments when Leo Messi met exceptional individuals from the blind community and gave them the gift of independence, OrCam MyEye.
OrCam MyEye is the world's most advanced assistive wearable device that reads text, recognizes faces, identifies…
  OrCam MyEye is the world's most advanced assistive wearable device that reads text, recognizes faces, identifies…
Microsoft releases a new version of DeepSpeed tool to enable the creation of deep learning models with a trillion parameters
Github: https://github.com/microsoft/DeepSpeed
Source: https://www.microsoft.com/en-us/research/project/deepspeed/
Paper: https://arxiv.org/abs/1910.02054
  
  Github: https://github.com/microsoft/DeepSpeed
Source: https://www.microsoft.com/en-us/research/project/deepspeed/
Paper: https://arxiv.org/abs/1910.02054
GitHub
  
  GitHub - deepspeedai/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training and inference…
  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. - deepspeedai/DeepSpeed
  tsBNgen, a Python Library to Generate Synthetic Data From an Arbitrary Bayesian Network.
Paper Summary: https://www.marktechpost.com/2020/09/15/tsbngen-a-python-library-to-generate-synthetic-data-from-an-arbitrary-bayesian-network/
Paper: https://arxiv.org/pdf/2009.04595.pdf
Github: https://github.com/manitadayon/tsBNgen/blob/master/tsbngen.pdf
  
  Paper Summary: https://www.marktechpost.com/2020/09/15/tsbngen-a-python-library-to-generate-synthetic-data-from-an-arbitrary-bayesian-network/
Paper: https://arxiv.org/pdf/2009.04595.pdf
Github: https://github.com/manitadayon/tsBNgen/blob/master/tsbngen.pdf
MarkTechPost
  
  tsBNgen, a Python Library to Generate Synthetic Data From an Arbitrary Bayesian Network.
  tsBNgen, a Python Library to Generate Time Series and Sequential Data Based on an Arbitrary Dynamic Bayesian Network.