Understanding Hinton’s Capsule Networks. Part I: Intuition.
Blog by Max Pechyonkin: https://medium.com/ai³-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b
#MachineLearning #DeepLearning #GeoffreyHinton #ArtificialIntelligence #Theory
Blog by Max Pechyonkin: https://medium.com/ai³-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b
#MachineLearning #DeepLearning #GeoffreyHinton #ArtificialIntelligence #Theory
Medium
Understanding Hinton’s Capsule Networks. Part I: Intuition.
Part of Understanding Hinton’s Capsule Networks Series:
Augmented Neural ODEs
Dupont et al.
Github: https://github.com/EmilienDupont/augmented-neural-odes
Paper: https://arxiv.org/abs/1904.01681
#ArtificialIntelligence #MachineLearning #Pytorch
Dupont et al.
Github: https://github.com/EmilienDupont/augmented-neural-odes
Paper: https://arxiv.org/abs/1904.01681
#ArtificialIntelligence #MachineLearning #Pytorch
GitHub
GitHub - EmilienDupont/augmented-neural-odes: Pytorch implementation of Augmented Neural ODEs :sunflower:
Pytorch implementation of Augmented Neural ODEs :sunflower: - EmilienDupont/augmented-neural-odes
FastSpeech: Fast, Robust and Controllable Text to Speech
speeds up the mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x
ArXiv
https://arxiv.org/abs/1905.09263
Samples
https://speechresearch.github.io/fastspeech/
speeds up the mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x
ArXiv
https://arxiv.org/abs/1905.09263
Samples
https://speechresearch.github.io/fastspeech/
arXiv.org
FastSpeech: Fast, Robust and Controllable Text to Speech
Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from...
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection #CVPR2019
Key component to close the gap between image & LiDAR based 3D object detection may be simply the representation of 3D information
SOTA on KITTI
https://arxiv.org/abs/1812.07179v4
Key component to close the gap between image & LiDAR based 3D object detection may be simply the representation of 3D information
SOTA on KITTI
https://arxiv.org/abs/1812.07179v4
arXiv.org
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D...
3D object detection is an essential task in autonomous driving. Recent
techniques excel with highly accurate detection rates, provided the 3D input
data is obtained from precise but expensive...
techniques excel with highly accurate detection rates, provided the 3D input
data is obtained from precise but expensive...
DeepRED: Deep Image Prior Powered by RED
Unsupervised restoration algorithm combines Deep Image Prior with the Regularization by Denoising (RED) while avoiding the need to differentiate the chosen denoiser
https://arxiv.org/abs/1903.10176
Unsupervised restoration algorithm combines Deep Image Prior with the Regularization by Denoising (RED) while avoiding the need to differentiate the chosen denoiser
https://arxiv.org/abs/1903.10176
Collections of Papers & Code on Domain Adaptation
https://github.com/zhaoxin94/awsome-domain-adaptation
https://github.com/zhaoxin94/awsome-domain-adaptation
GitHub
GitHub - zhaoxin94/awesome-domain-adaptation: A collection of AWESOME things about domian adaptation
A collection of AWESOME things about domian adaptation - GitHub - zhaoxin94/awesome-domain-adaptation: A collection of AWESOME things about domian adaptation
"Introduction to Deep Learning" Course
Slides, course materials, demos, and implementations
https://chokkan.github.io/deeplearning/
Slides, course materials, demos, and implementations
https://chokkan.github.io/deeplearning/
Myia is a new differentiable programming language. It aims to support large scale high performance computations (e.g. linear algebra) and their gradients. The main application Myia aims to support is research in artificial intelligence, in particular deep learning algorithms.
https://github.com/mila-iqia/myia
https://github.com/mila-iqia/myia
GitHub
GitHub - mila-iqia/myia: Myia prototyping
Myia prototyping. Contribute to mila-iqia/myia development by creating an account on GitHub.
LSTM Autoencoder for Extreme Rare Event Classification in Keras
Ranjan et al.: https://towardsdatascience.com/lstm-autoencoder-for-extreme-rare-event-classification-in-keras-ce209a224cfb
#DeepLearning #DataScience #ArtificialIntelligence #DataScience
Ranjan et al.: https://towardsdatascience.com/lstm-autoencoder-for-extreme-rare-event-classification-in-keras-ce209a224cfb
#DeepLearning #DataScience #ArtificialIntelligence #DataScience
Medium
LSTM Autoencoder for Extreme Rare Event Classification in Keras
Here we will learn the details of data preparation for LSTM models, and build an LSTM Autoencoder for rare-event classification in Keras.
"Wasserstein GAN"
Written by James Allingham: https://www.depthfirstlearning.com/2019/WassersteinGAN
#DeepLearning #GenerativeModels #GenerativeAdversarialNetworks
Written by James Allingham: https://www.depthfirstlearning.com/2019/WassersteinGAN
#DeepLearning #GenerativeModels #GenerativeAdversarialNetworks
Microsoft launches a drag-and-drop machine learning tool
Article by Frederic Lardinois: https://techcrunch.com/2019/05/02/microsoft-launches-a-drag-and-drop-machine-learning-tool-and-hosted-jupyter-notebooks/
#ArtificialIntelligence #DeepLearning #MachineLearning
Article by Frederic Lardinois: https://techcrunch.com/2019/05/02/microsoft-launches-a-drag-and-drop-machine-learning-tool-and-hosted-jupyter-notebooks/
#ArtificialIntelligence #DeepLearning #MachineLearning
TechCrunch
Microsoft launches a drag-and-drop machine learning tool
Microsoft today announced three new services that all aim to simplify the process of machine learning. These range from a new interface for a tool that completely automates the process of creating models, to a new no-code visual interface for building, training…
Datasheets for Datasets
Gebru et al.: https://arxiv.org/abs/1803.09010
#Databases #ArtificialIntelligence #AIEthics #Ethics #MachineLearning
Gebru et al.: https://arxiv.org/abs/1803.09010
#Databases #ArtificialIntelligence #AIEthics #Ethics #MachineLearning
arXiv.org
Datasheets for Datasets
The machine learning community currently has no standardized process for documenting datasets, which can lead to severe consequences in high-stakes domains. To address this gap, we propose...
Minicourse in Deep Learning with PyTorch
By Alfredo Canziani: https://github.com/Atcold/pytorch-Deep-Learning-Minicourse
#DeepLearning #MachineLearning #PyTorch
By Alfredo Canziani: https://github.com/Atcold/pytorch-Deep-Learning-Minicourse
#DeepLearning #MachineLearning #PyTorch
GitHub
GitHub - Atcold/NYU-DLSP20: NYU Deep Learning Spring 2020
NYU Deep Learning Spring 2020. Contribute to Atcold/NYU-DLSP20 development by creating an account on GitHub.
State of the art video editing - make any object in a video invisible!
Deep Flow-Guided Video Inpainting
paper: https://www.profillic.com/paper/arxiv:1905.02884
Deep Flow-Guided Video Inpainting
paper: https://www.profillic.com/paper/arxiv:1905.02884
Profillic
Profillic: AI research & source code to supercharge your projects
Explore state-of-the-art in machine learning, AI, and robotics research. Browse papers, source code, models, and more by topics and authors. Connect with researchers and engineers working on related problems in machine learning, deep learning, natural language…
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
https://github.com/kmario23/deep-learning-drizzle
https://github.com/kmario23/deep-learning-drizzle
GitHub
GitHub - kmario23/deep-learning-drizzle: Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision…
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!! - kmario23/deep-learning-drizzle
Canada is Failing in Applied AI Innovation
"Canada is failing in Applied AI innovation and the impact will be severe unless everyone leads in new and more powerful intentionality ways."
Article by Dr. Cindy Gordon: https://cata.ca/2019/ai-innovation-lagging/
#ArtificialIntelligence #Canada #Governance
"Canada is failing in Applied AI innovation and the impact will be severe unless everyone leads in new and more powerful intentionality ways."
Article by Dr. Cindy Gordon: https://cata.ca/2019/ai-innovation-lagging/
#ArtificialIntelligence #Canada #Governance
Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making
Cai et al.: https://arxiv.org/abs/1902.02960
#humancentered #machinelearning #medical #innovation #technology
Cai et al.: https://arxiv.org/abs/1902.02960
#humancentered #machinelearning #medical #innovation #technology
DL app that turns UI screenshots into a Bootstrap implementation. https://news.developer.nvidia.com/ai-turns-ui-designs-into…/
The code is open-source! https://github.com/tonybeltramelli/pix2code
The code is open-source! https://github.com/tonybeltramelli/pix2code
Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
Belinda Tzen and Maxim Raginsky: https://arxiv.org/abs/1905.09883
#ArtificialIntelligence #DifferentialEquation #MachineLearning
Belinda Tzen and Maxim Raginsky: https://arxiv.org/abs/1905.09883
#ArtificialIntelligence #DifferentialEquation #MachineLearning
New "Simple Self Attention" Layer
GitHub by Sébastien Doria: https://github.com/sdoria/SimpleSelfAttention
#MachineLearning #Pytorch #FastAI #SelfAttention
GitHub by Sébastien Doria: https://github.com/sdoria/SimpleSelfAttention
#MachineLearning #Pytorch #FastAI #SelfAttention