"Accelerating Deep Learning Research with the Tensor2Tensor Library"+trained translation model releases of: SliceNet, ByteNet, GNMT, Mixture-GNMT, Attention is all You Need
https://research.googleblog.com/2017/06/accelerating-deep-learning-research.html
https://research.googleblog.com/2017/06/accelerating-deep-learning-research.html
Googleblog
Accelerating Deep Learning Research with the Tensor2Tensor Library
Using ANNs on small data – Deep Learning vs. Xgboost
http://maxberggren.se/2017/06/18/deep-learning-vs-xgboost/
http://maxberggren.se/2017/06/18/deep-learning-vs-xgboost/
maxberggren.se
Using ANNs on small data – Deep Learning vs. Xgboost
Andrew Beam does a great job showing that small datasets are not off limits for current neural net methods. If you use the regularisation methods at hand – A...
Practical Deep OCR for scene text using CTPN + CRNN
https://github.com/AKSHAYUBHAT/DeepVideoAnalytics/blob/master/notebooks/OCR/readme.md
https://github.com/AKSHAYUBHAT/DeepVideoAnalytics/blob/master/notebooks/OCR/readme.md
GitHub
AKSHAYUBHAT/DeepVideoAnalytics
DeepVideoAnalytics - A distributed visual search and visual data analytics platform.
Machine Learning for Image Content Analysis
https://exploreai.org/p/machine-learning-image-content-analysis
https://exploreai.org/p/machine-learning-image-content-analysis
exploreai.org
Machine Learning - Image Content Analysis
Human and Machine Judgements about Russian Semantic Relatedness
http://russe.nlpub.ru/downloads/
http://russe.nlpub.ru/downloads/
A Jupyter Notebook collecting the state of the art on numerous ML benchmarks
https://www.eff.org/ai/metrics
https://www.eff.org/ai/metrics
Matrix Factorization in PyTorch
http://blog.ethanrosenthal.com/2017/06/20/matrix-factorization-in-pytorch/
http://blog.ethanrosenthal.com/2017/06/20/matrix-factorization-in-pytorch/
LSTM – сети долгой краткосрочной памяти
https://habrahabr.ru/company/wunderfund/blog/331310/
https://habrahabr.ru/company/wunderfund/blog/331310/
Habr
LSTM – сети долгой краткосрочной памяти
Рекуррентные нейронные сети Люди не начинают думать с чистого листа каждую секунду. Читая этот пост, вы понимаете каждое слово, основываясь на понимании предыдущего слова. Мы не выбрасываем из головы...
MultiModel: Multi-Task Machine Learning Across Domains
https://research.googleblog.com/2017/06/multimodel-multi-task-machine-learning.html
https://research.googleblog.com/2017/06/multimodel-multi-task-machine-learning.html
Google AI Blog
MultiModel: Multi-Task Machine Learning Across Domains
Posted by Łukasz Kaiser, Senior Research Scientist, Google Brain Team and Aidan N. Gomez, Researcher, Department of Computer Science Machine...
Great list of podcasts if you are interested in Data Science
http://byteacademy.co/blog/data-science-podcasts
http://byteacademy.co/blog/data-science-podcasts
Byte Academy
10 Data Science Podcasts You Need To be Listening To Right Now - Byte Academy
Keep up with the latest developments in data science and artificial intelligence with Byte Academy’s recommended list of data science podcasts.
How to Handle Missing Timesteps in Sequence Prediction Problems with Python
http://machinelearningmastery.com/handle-missing-timesteps-sequence-prediction-problems-python/
http://machinelearningmastery.com/handle-missing-timesteps-sequence-prediction-problems-python/
MachineLearningMastery.com
How to Handle Missing Timesteps in Sequence Prediction Problems with Python - MachineLearningMastery.com
It is common to have missing observations from sequence data.
Data may be corrupt or unavailable, but it is also possible that your data has variable length sequences by definition. Those sequences with fewer timesteps may be considered to have missing…
Data may be corrupt or unavailable, but it is also possible that your data has variable length sequences by definition. Those sequences with fewer timesteps may be considered to have missing…
Building a Real-Time Object Recognition App with Tensorflow and OpenCV (With nice multithread OpenCV -> TF pipeline for efficient I/O)
https://medium.com/towards-data-science/building-a-real-time-object-recognition-app-with-tensorflow-and-opencv-b7a2b4ebdc32
https://medium.com/towards-data-science/building-a-real-time-object-recognition-app-with-tensorflow-and-opencv-b7a2b4ebdc32
Medium
Building a Real-Time Object Recognition App with Tensorflow and OpenCV
In this article, I will walk through the steps how you can easily build your own real-time object recognition application with Tensorflow’s…
Recommending GitHub Repositories with Google BigQuery and the implicit library
https://medium.com/towards-data-science/recommending-github-repositories-with-google-bigquery-and-the-implicit-library-e6cce666c77
https://medium.com/towards-data-science/recommending-github-repositories-with-google-bigquery-and-the-implicit-library-e6cce666c77
Medium
Recommending GitHub Repositories with Google BigQuery and the implicit library
Keeping track of all the great repositories that are published in GitHub is an impossible task. The trending list does not help much. As…
Keras-vis: Toolkit to perform guided backprop for neural network visualizations
https://github.com/raghakot/keras-vis
https://github.com/raghakot/keras-vis
GitHub
GitHub - raghakot/keras-vis: Neural network visualization toolkit for keras
Neural network visualization toolkit for keras. Contribute to raghakot/keras-vis development by creating an account on GitHub.
Implementation of Sparse Variational Dropout
https://github.com/ars-ashuha/variational-dropout-sparsifies-dnn
https://github.com/ars-ashuha/variational-dropout-sparsifies-dnn
GitHub
senya-ashukha/variational-dropout-sparsifies-dnn
Sparse Variational Dropout, ICML 2017. Contribute to senya-ashukha/variational-dropout-sparsifies-dnn development by creating an account on GitHub.
Автоэнкодеры в Keras, Часть 4: Conditional VAE
https://habrahabr.ru/post/331664/
https://habrahabr.ru/post/331664/
Habr
Автоэнкодеры в Keras, Часть 4: Conditional VAE
Содержание Часть 1: Введение Часть 2: Manifold learning и скрытые ( latent ) переменные Часть 3: Вариационные автоэнкодеры ( VAE ) Часть 4: Conditional VAE Часть 5: GAN (Generative Adversarial...