When Does Label Smoothing Help?
by Rafael Müller, Simon Kornblith, Geoffrey Hinton
https://arxiv.org/abs/1906.02629v1
by Rafael Müller, Simon Kornblith, Geoffrey Hinton
https://arxiv.org/abs/1906.02629v1
arXiv.org
When Does Label Smoothing Help?
The generalization and learning speed of a multi-class neural network can
often be significantly improved by using soft targets that are a weighted
average of the hard targets and the uniform...
often be significantly improved by using soft targets that are a weighted
average of the hard targets and the uniform...
Countdown Regression: Sharp and Calibrated Survival Predictions by Andrew Ng , Anand Avati, Tony Duan, Sharon Zhou, Kenneth Jung, Nigam H. Shah https://arxiv.org/abs/1806.08324v2
The future depends on some graduate student who is deeply suspicious of everything I have said. - Geoffrey Hinton https://t.iss.one/ArtificialIntelligenceArticles
Real-Time AR Self-Expression with Machine Learning
Augmented reality (AR) helps you do more with what you see by overlaying digital content and information on top of the physical world. For example, AR features coming to Google Maps will let you find your way with directions overlaid on top of your real world. With Playground - a creative mode in the Pixel camera -- you can use AR to see the world differently. And with the latest release of YouTube Stories and ARCore's new Augmented Faces API you can add objects like animated masks, glasses, 3D hats and more to your own selfies!
Direct Link: https://ai.googleblog.com/2019/03/real-time-ar-self-expression-with.html
Augmented reality (AR) helps you do more with what you see by overlaying digital content and information on top of the physical world. For example, AR features coming to Google Maps will let you find your way with directions overlaid on top of your real world. With Playground - a creative mode in the Pixel camera -- you can use AR to see the world differently. And with the latest release of YouTube Stories and ARCore's new Augmented Faces API you can add objects like animated masks, glasses, 3D hats and more to your own selfies!
Direct Link: https://ai.googleblog.com/2019/03/real-time-ar-self-expression-with.html
Googleblog
Real-Time AR Self-Expression with Machine Learning
[#basics][#deeplearningdevelopment]
0. Programming doubts, dont know where to ask, pls here first ?
https://stackoverflow.com/
0.1 Software versioning, software managing and production GIT
https://git-scm.com/book/en/v1/Getting-Started-Git-Basics
0.1.1 Searching for code that does something ?
https://github.com/
google for: https://github.com/repo: <term>
1. Python Programming, many references
https://www.fullstackpython.com/python-programming-language.html
A . Deep Learning Elementary Lectures by Geof Hinton
https://www.cs.toronto.edu/~hinton/coursera_lectures.html
A.1 Tensorflow Repository/**Documentation** and Issue Tracker (most popular and effective Deep Learning framework)
Issues: https://github.com/tensorflow/tensorflow/issues
Docs: https://www.tensorflow.org/api_docs/python/tf
A.2 Keras Mailing List (High Level Python Tensorflow API)
https://groups.google.com/forum/#!forum/keras-users
A.3 Tensorflow Computational Graphs Explained From Scratch
https://www.deepideas.net/deep-learning-from-scratch-i-computational-graphs/
B. Conda, One of the most impressives python virtual environment managers, essential for python development,
https://conda.io/en/latest/
B.0 Create virtual env only with the Conda manager and its dependencies: Miniconda
https://docs.conda.io/en/latest/miniconda.html
B.1 Anaconda, big Python Libs Distros
https://www.anaconda.com/
C. Conda Virtual Envs with Docker
https://medium.com/@chadlagore/conda-environments-with-docker-82cdc9d25754
0. Programming doubts, dont know where to ask, pls here first ?
https://stackoverflow.com/
0.1 Software versioning, software managing and production GIT
https://git-scm.com/book/en/v1/Getting-Started-Git-Basics
0.1.1 Searching for code that does something ?
https://github.com/
google for: https://github.com/repo: <term>
1. Python Programming, many references
https://www.fullstackpython.com/python-programming-language.html
A . Deep Learning Elementary Lectures by Geof Hinton
https://www.cs.toronto.edu/~hinton/coursera_lectures.html
A.1 Tensorflow Repository/**Documentation** and Issue Tracker (most popular and effective Deep Learning framework)
Issues: https://github.com/tensorflow/tensorflow/issues
Docs: https://www.tensorflow.org/api_docs/python/tf
A.2 Keras Mailing List (High Level Python Tensorflow API)
https://groups.google.com/forum/#!forum/keras-users
A.3 Tensorflow Computational Graphs Explained From Scratch
https://www.deepideas.net/deep-learning-from-scratch-i-computational-graphs/
B. Conda, One of the most impressives python virtual environment managers, essential for python development,
https://conda.io/en/latest/
B.0 Create virtual env only with the Conda manager and its dependencies: Miniconda
https://docs.conda.io/en/latest/miniconda.html
B.1 Anaconda, big Python Libs Distros
https://www.anaconda.com/
C. Conda Virtual Envs with Docker
https://medium.com/@chadlagore/conda-environments-with-docker-82cdc9d25754
Stack Overflow
Newest Questions
Stack Overflow | The World’s Largest Online Community for Developers
Clothing Identification Tech from CVPR 2019!
paper: [https://www.profillic.com/paper/arxiv:1901.07973](https://www.profillic.com/paper/arxiv:1901.07973?fbclid=IwAR3bIPaWZk4Plhug0SvKdQt96dR8eAPqPgK7YX4TKlMkHC8OH5vVHwUjsao)
Deepfashion 2 provides a new benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
(The dataset contains 491K diverse images of 13 popular clothing categories from both commercial shopping stores and consumers)
paper: [https://www.profillic.com/paper/arxiv:1901.07973](https://www.profillic.com/paper/arxiv:1901.07973?fbclid=IwAR3bIPaWZk4Plhug0SvKdQt96dR8eAPqPgK7YX4TKlMkHC8OH5vVHwUjsao)
Deepfashion 2 provides a new benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
(The dataset contains 491K diverse images of 13 popular clothing categories from both commercial shopping stores and consumers)
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…
The first AI universe sim is fast and accurate—and its creators don't know how it works
https://phys.org/news/2019-06-ai-universe-sim-fast-accurateand.html
https://phys.org/news/2019-06-ai-universe-sim-fast-accurateand.html
phys.org
The first AI universe sim is fast and accurate—and its creators don't know how it works
For the first time, astrophysicists have used artificial intelligence techniques to generate complex 3-D simulations of the universe. The results are so fast, accurate and robust that even the creators ...
Applied Data Scientists / Quantitative Researchers (Stats, Machine Learning, Python/R) @ YELP London
We are looking for Applied Data Scientists / Quantitative Researchers to join our London team. Please visit the
following link for more info: https://www.yelp.com/careers/job-openings/8c288764-b1db-4b72-ac75-07b34c9f9b74
We are looking for Applied Data Scientists / Quantitative Researchers to join our London team. Please visit the
following link for more info: https://www.yelp.com/careers/job-openings/8c288764-b1db-4b72-ac75-07b34c9f9b74
Yelp
Quantitative Researcher (Stats, Machine Learning, Python/R) - Engineering - London, UK - Careers at Yelp
Join our Engineering team and help millions of people connect with local businesses on Yelp.
For those who are interested in healthcare : Machine Learning for Healthcare 2019
https://www.mlforhc.org/
https://www.mlforhc.org/
Training an AI agent to play Snake with TensorFlow 2.0.
Code by Paweł Kieliszczyk: https://github.com/pawel-kieliszczyk/snake-reinforcement-learning
#MachineLearning #ReinforcementLearning #TensorFlow
Code by Paweł Kieliszczyk: https://github.com/pawel-kieliszczyk/snake-reinforcement-learning
#MachineLearning #ReinforcementLearning #TensorFlow
GitHub
GitHub - pawel-kieliszczyk/snake-reinforcement-learning: AI (A2C agent) mastering the game of Snake with TensorFlow 2.0
AI (A2C agent) mastering the game of Snake with TensorFlow 2.0 - GitHub - pawel-kieliszczyk/snake-reinforcement-learning: AI (A2C agent) mastering the game of Snake with TensorFlow 2.0
Fast Training of Sparse Graph Neural Networks on Dense Hardware
Balog et al.: https://arxiv.org/abs/1906.11786
#artificialintelligence #neuralnetworks #machinelearning #datascience
Balog et al.: https://arxiv.org/abs/1906.11786
#artificialintelligence #neuralnetworks #machinelearning #datascience
Growing Action Spaces
Farquhar et al.: https://arxiv.org/abs/1906.12266
#deeplearning #machinelearning #reinforcementlearning
Farquhar et al.: https://arxiv.org/abs/1906.12266
#deeplearning #machinelearning #reinforcementlearning
PhD fellow in Theoretical Machine Learning
University of Copenhagen, Denmark
More Details: https://www.marktechpost.com/job/phd-fellow-in-theoretical-machine-learning/
Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship in Theoretical Machine Learning commencing 01.10.2019 or as soon as possible thereafter.
University of Copenhagen, Denmark
More Details: https://www.marktechpost.com/job/phd-fellow-in-theoretical-machine-learning/
Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship in Theoretical Machine Learning commencing 01.10.2019 or as soon as possible thereafter.
How do neural networks see depth in single images?
https://arxiv.org/pdf/1905.07005.pdf
https://arxiv.org/pdf/1905.07005.pdf
"Machine Learning Systems are Stuck in a Rut"
By Paul Barham and Michael Isard: https://dl.acm.org/citation.cfm?id=3321441
#TensorFlow #PyTorch #Swift #MachineLearning
By Paul Barham and Michael Isard: https://dl.acm.org/citation.cfm?id=3321441
#TensorFlow #PyTorch #Swift #MachineLearning
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
Maksym Andriushchenko and Matthias Hein: https://arxiv.org/abs/1906.03526
Code: https://github.com/max-andr/provably-robust-boosting
#MachineLearning #Cryptography #Security
Maksym Andriushchenko and Matthias Hein: https://arxiv.org/abs/1906.03526
Code: https://github.com/max-andr/provably-robust-boosting
#MachineLearning #Cryptography #Security
arXiv.org
Provably Robust Boosted Decision Stumps and Trees against...
The problem of adversarial robustness has been studied extensively for neural
networks. However, for boosted decision trees and decision stumps there are
almost no results, even though they are...
networks. However, for boosted decision trees and decision stumps there are
almost no results, even though they are...