The danger of artificial intelligence isn't that it's going to rebel against us, but that it's going to do exactly what we ask it to do, says AI researcher Janelle Shane. Sharing the weird, sometimes alarming antics of AI algorithms as they try to solve human problems -- like creating new ice cream flavors or recognizing cars on the road -- Shane shows why AI doesn't yet measure up to real brains.
https://www.youtube.com/watch?v=OhCzX0iLnOc
https://www.youtube.com/watch?v=OhCzX0iLnOc
YouTube
The danger of AI is weirder than you think | Janelle Shane
Visit https://TED.com to get our entire library of TED Talks, transcripts, translations, personalized Talk recommendations and more.
The danger of artificial intelligence isn't that it's going to rebel against us, but that it's going to do exactly what we…
The danger of artificial intelligence isn't that it's going to rebel against us, but that it's going to do exactly what we…
The Illustrated GPT-2 (Visualizing Transformer Language Models)
Blog by Jay Alammar : https://jalammar.github.io/illustrated-gpt2/
#ArtificialIntelligence #NLP #UnsupervisedLearning
Blog by Jay Alammar : https://jalammar.github.io/illustrated-gpt2/
#ArtificialIntelligence #NLP #UnsupervisedLearning
Conditionally Learn to Pay Attention for Sequential Visual Task
He et al.: https://arxiv.org/abs/1911.04365
#ArtificialIntelligence #DeepLearning #MachineLearning
He et al.: https://arxiv.org/abs/1911.04365
#ArtificialIntelligence #DeepLearning #MachineLearning
arXiv.org
Conditionally Learn to Pay Attention for Sequential Visual Task
Sequential visual task usually requires to pay attention to its current
interested object conditional on its previous observations. Different from
popular soft attention mechanism, we propose a...
interested object conditional on its previous observations. Different from
popular soft attention mechanism, we propose a...
Machine Learning:
Mathematical Theory
and Scientific Applications https://www.ams.org/journals/notices/201911/rnoti-p1813.pdf
Mathematical Theory
and Scientific Applications https://www.ams.org/journals/notices/201911/rnoti-p1813.pdf
ArtificialIntelligenceArticles
Does the brain do backpropagation? CAN Public Lecture - Geoffrey Hinton One of the best recent talks of Prof. Geoffrey Hinton online on computation in the brain. Intriguingly, the proposed relation between the neuron firing rate and the error signal looks…
Calculating the Backpropagation of a Network
https://medium.com/towards-artificial-intelligence/calculating-back-propagation-of-a-network-1febbcaa2b5d
https://medium.com/towards-artificial-intelligence/calculating-back-propagation-of-a-network-1febbcaa2b5d
Medium
Calculating the Backpropagation of a Network
A beginner’s guide to the math behind the backpropagation algorithm
CIFAR réalise une interview avec Yoshua Bengio, notre scientifique en chef à #CDLMontréal, pour leur série intitulée "The Brains Behind AI". À voir !
//
CIFAR interviews #CDLMontreal’s chief scientist Yoshua Bengio for their series titled “The Brains Behind AI”. Watch it! https://www.youtube.com/watch?list=PLhzeDL-FIJK88ULiQAweocXsM_mqDwhBz&v=O6TgVE3JHfs&feature=emb_title&fbclid=IwAR3-Fj_BqR2bTgG8CgiuPxc_HEgMJb-2Ab8tLE_oVHwagDY8N4mErHd0db8&utm_source=facebook&utm_medium=lickstats&utm_campaign=yoshuabengiovideo&utm_term=&utm_content=5dd01c5e5622932605205fbf
//
CIFAR interviews #CDLMontreal’s chief scientist Yoshua Bengio for their series titled “The Brains Behind AI”. Watch it! https://www.youtube.com/watch?list=PLhzeDL-FIJK88ULiQAweocXsM_mqDwhBz&v=O6TgVE3JHfs&feature=emb_title&fbclid=IwAR3-Fj_BqR2bTgG8CgiuPxc_HEgMJb-2Ab8tLE_oVHwagDY8N4mErHd0db8&utm_source=facebook&utm_medium=lickstats&utm_campaign=yoshuabengiovideo&utm_term=&utm_content=5dd01c5e5622932605205fbf
ArtificialIntelligenceArticles
CIFAR réalise une interview avec Yoshua Bengio, notre scientifique en chef à #CDLMontréal, pour leur série intitulée "The Brains Behind AI". À voir ! // CIFAR interviews #CDLMontreal’s chief scientist Yoshua Bengio for their series titled “The Brains Behind…
YouTube
Les cerveaux derrière l’IA: Yoshua Bengio
L’IA peut-elle résoudre le mystère de l’intelligence humaine et animale ? Yoshua Bengio, titulaire d’une chaire en IA Canada-CIFAR, est un pionnier de la rec...
Stacked Capsule Autoencoders
Adam R. Kosiorek, Sara Sabour, Yee Whye Teh, Geoffrey E. Hinton : https://arxiv.org/abs/1906.06818
Code : https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders
#ArtificialIntelligence #DeepLearning #MachineLearning
Adam R. Kosiorek, Sara Sabour, Yee Whye Teh, Geoffrey E. Hinton : https://arxiv.org/abs/1906.06818
Code : https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders
#ArtificialIntelligence #DeepLearning #MachineLearning
Learning Keypoint Representations for Robot Manipulation
Yuke Zhu, IROS 2019 : https://ai.stanford.edu/~yukez/talks/keypoint_representations_for_interaction.pdf
#ArtificialIntelligence #DeepLearning #Robotics
Yuke Zhu, IROS 2019 : https://ai.stanford.edu/~yukez/talks/keypoint_representations_for_interaction.pdf
#ArtificialIntelligence #DeepLearning #Robotics
Learning Neural Causal Models from Unknown Interventions
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio : https://arxiv.org/abs/1910.01075
#MetaLearning #MachineLearning #ArtificialIntelligence
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio : https://arxiv.org/abs/1910.01075
#MetaLearning #MachineLearning #ArtificialIntelligence
arXiv.org
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data. However, there are theoretical...
Recurrent Independent Mechanisms
Goyal et al.: https://arxiv.org/abs/1909.10893
#MachineLearning #DeepLearning #ArtificialIntelligence
Goyal et al.: https://arxiv.org/abs/1909.10893
#MachineLearning #DeepLearning #ArtificialIntelligence
arXiv.org
Recurrent Independent Mechanisms
Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes. We propose...
Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs
Alexia Jolicoeur-Martineau, Ioannis Mitliagkas : https://arxiv.org/abs/1910.06922
#PyTorch code: https://github.com/AlexiaJM/MaximumMarginGANs
#SupportVectorMachines #GenerativeAdversarialNetworks
Alexia Jolicoeur-Martineau, Ioannis Mitliagkas : https://arxiv.org/abs/1910.06922
#PyTorch code: https://github.com/AlexiaJM/MaximumMarginGANs
#SupportVectorMachines #GenerativeAdversarialNetworks
arXiv.org
Gradient penalty from a maximum margin perspective
A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated...
Evolving Neural Networks
A tutorial on evolutionary algorithms
Blog by Conor Lazarou : https://towardsdatascience.com/evolving-neural-networks-b24517bb3701
#EvolutionaryAlgorithms #NeuralNetworks #ReinforcementLearning
A tutorial on evolutionary algorithms
Blog by Conor Lazarou : https://towardsdatascience.com/evolving-neural-networks-b24517bb3701
#EvolutionaryAlgorithms #NeuralNetworks #ReinforcementLearning
Medium
Evolving Neural Networks
For the past decade, deep learning has dominated the machine learning landscape, often to the exclusion of other techniques. As a data…
PaperRobot: Incremental Draft Generation of Scientific Ideas
Wang et al.: https://arxiv.org/abs/1905.07870
#ArtificialIntelligence #MachineLearning #DeepLearning
Wang et al.: https://arxiv.org/abs/1905.07870
#ArtificialIntelligence #MachineLearning #DeepLearning
arXiv.org
PaperRobot: Incremental Draft Generation of Scientific Ideas
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing...
Open-Source RL Algorithms
By Sergey Kolesnikov : https://docs.google.com/spreadsheets/d/1EeFPd-XIQ3mq_9snTlAZSsFY7Hbnmd7P5bbT8LPuMn0/
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
By Sergey Kolesnikov : https://docs.google.com/spreadsheets/d/1EeFPd-XIQ3mq_9snTlAZSsFY7Hbnmd7P5bbT8LPuMn0/
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
Google Docs
Open-source RL
Frameworks
Execution,Algorithms (discrete / continuous / both),Additional features
Project,link,Maintainer,Framework,Parallel,Distributed,DQN,Rainbow,REINFORCE,A2C,PPO,DDPG,SAC,TD3,REINFORCE,A2C,PPO,TRPO,GAIL,n-step
return
<a href="https://github.com/o…
Execution,Algorithms (discrete / continuous / both),Additional features
Project,link,Maintainer,Framework,Parallel,Distributed,DQN,Rainbow,REINFORCE,A2C,PPO,DDPG,SAC,TD3,REINFORCE,A2C,PPO,TRPO,GAIL,n-step
return
<a href="https://github.com/o…
This Open Sourced Python library ‘audit-AI’ does Bias Testing for Generalized Machine Learning Applications
Github Link: https://github.com/pymetrics/audit-ai
Related Paper: https://arxiv.org/pdf/1906.09208.pdf
Github Link: https://github.com/pymetrics/audit-ai
Related Paper: https://arxiv.org/pdf/1906.09208.pdf
GitHub
GitHub - pymetrics/audit-ai: detect demographic differences in the output of machine learning models or other assessments
detect demographic differences in the output of machine learning models or other assessments - pymetrics/audit-ai
Accelerating TSNE with GPUs: From hours to seconds
Blog by Daniel Han-Chen : https://medium.com/rapids-ai/tsne-with-gpus-hours-to-seconds-9d9c17c941db
#MachineLearning #DataVisualization #DataScience
Blog by Daniel Han-Chen : https://medium.com/rapids-ai/tsne-with-gpus-hours-to-seconds-9d9c17c941db
#MachineLearning #DataVisualization #DataScience
Medium
Accelerating TSNE with GPUs: From hours to seconds
RAPIDS TSNE runs 2000x faster on GPUs — That’s 3 hours down to 5 seconds!
Learning Data Manipulation for Augmentation and Weighting
Hu et al.: https://arxiv.org/abs/1910.12795
Code: https://github.com/tanyuqian/learning-data-manipulation
#ArtificialIntelligence #DeepLearning #NeurIPS2019
Hu et al.: https://arxiv.org/abs/1910.12795
Code: https://github.com/tanyuqian/learning-data-manipulation
#ArtificialIntelligence #DeepLearning #NeurIPS2019
Exploring the Origins and Prevalence of Texture Bias in Convolutional Neural Networks
Katherine L. Hermann, Simon Kornblith : https://arxiv.org/abs/1911.09071
#ArtificialIntelligence #DeepLearning #NeuralNetworks
Katherine L. Hermann, Simon Kornblith : https://arxiv.org/abs/1911.09071
#ArtificialIntelligence #DeepLearning #NeuralNetworks
Continual Unsupervised Representation Learning
Rao et al.: https://arxiv.org/abs/1910.14481
Code: https://github.com/deepmind/deepmind-research/tree/master/curl
#ArtificialIntelligence #DeepLearning #NeurIPS2019
Rao et al.: https://arxiv.org/abs/1910.14481
Code: https://github.com/deepmind/deepmind-research/tree/master/curl
#ArtificialIntelligence #DeepLearning #NeurIPS2019