First Telegram Data Science channel. Covering all technical and popular staff about anything related to Data Science: AI, Big Data, Machine Learning, Statistics, general Math and the applications of former. To reach editors contact: @malev
Google's open source candy for all ML community:
Source-to-Source Debuggable Derivatives
https://opensource.googleblog.com/2017/11/tangent-source-to-source-debuggable.html?m=1
#opensource #nn #python #google
The State of Data Science & Machine Learning 2017 by Kaggle.
Very informative article about age, job titles, most popular languages and everything related to DS / ML.
Not to mention that source data is included.
https://www.kaggle.com/surveys/2017
#kaggle #statistics
Winning approaches for solving Advanced Driver Assistance System challenge on Kaggle:
https://blog.getnexar.com/how-a-22-year-old-from-shanghai-won-a-global-deep-learning-challenge-76f2299446a1
#deeplearning #kaggle #cv
https://twitter.com/pleonard/status/914671877146206208
Читать полностью…NLP for beginners
http://blog.kaggle.com/2017/08/25/data-science-101-getting-started-in-nlp-tokenization-tutorial/
#tutorial #nlp
Comparison of 13 classic ML algorithms on 165 datasets.
https://arxiv.org/pdf/1708.05070.pdf
#meta #arxiv #ml
Neural net for removing copyright marks.
https://www.theverge.com/2017/8/18/16162108/google-research-algorithm-watermark-removal-photo-protection
#cv #dl #google
2900 members, hoooray!
Thank you all for sharing posts, for suggesting content throught @opendatasciencebot. Hope that our channel is useful for you and your research / study / work.
Tutorial on Building a Facial Recognition Pipeline with Deep Learning in Tensorflow
https://hackernoon.com/building-a-facial-recognition-pipeline-with-deep-learning-in-tensorflow-66e7645015b8
#facerecognition #dl #tensorflow #cv #tutorial
Deep Bilateral Learning for Real-Time Image Enhancement
Video about image auto-enhancing with neural networks.
https://www.youtube.com/watch?v=GAe0qKKQY_I
#cv #dl #autoenhance #mit #youtube #video
Nice place to start with text mining with neural networks.
http://ruder.io/deep-learning-nlp-best-practices/
#nlp #dl #where2start
Andrew Ng has announced new Deep Learning course on Coursera:
“deeplearning.ai: Announcing new Deep Learning courses on Coursera” andrewng/deeplearning-ai-announcing-new-deep-learning-courses-on-coursera-43af0a368116" rel="nofollow">https://medium.com/@andrewng/deeplearning-ai-announcing-new-deep-learning-courses-on-coursera-43af0a368116
#coursera #deep_learning earning #dl #andrewng
Non-NLP application of Word2Vec
https://medium.com/towards-data-science/a-non-nlp-application-of-word2vec-c637e35d3668
#nlp #w2v @word2vec
https://www.technologyreview.com/s/603007/robot-cars-can-learn-to-drive-without-leaving-the-garage/
Читать полностью…Release of a nice NLP-processing library.
https://www.techleer.com/articles/404-spacy-20-released-natural-language-processing-with-python/
#nlp #python
Great example of feature visualisation
https://distill.pub/2017/feature-visualization/
ARkit Sudoku solver built with CoreML
https://blog.prototypr.io/behind-the-magic-how-we-built-the-arkit-sudoku-solver-e586e5b685b0
#ar #cv #keras #coreml
Another breakthrough with generative models.
BEGAN: Boundary Equilibrium Generative Adversarial Networks
https://arxiv.org/abs/1703.10717
#gan #cv
Netflix shared its recommendation engine scheme:
https://medium.com/netflix-techblog/distributed-time-travel-for-feature-generation-389cccdd3907
#ml #rs #spark #hadoop
Architecture for real-time scene annotation (BlitzNet)
http://thoth.inrialpes.fr/research/blitznet/
ArxiV: https://arxiv.org/abs/1708.02813
GitHub: https://github.com/dvornikita/blitznet
#ICCV #github #dl #video
Beautiful thematic maps with ggplot2
https://timogrossenbacher.ch/2016/12/beautiful-thematic-maps-with-ggplot2-only/
#viz #ggplot #maps
Tutorial on how to launch Jupyter Notebook in Google GPU cloud.
https://hackernoon.com/launch-a-gpu-backed-google-compute-engine-instance-and-setup-tensorflow-keras-and-jupyter-902369ed5272
#tutorial #jupyter #google
STMVis - Visual Analysis for Recurrent Neural Networks
LSTMVis a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows a user to select a hypothesis input range to focus on local state changes, to match these states changes to similar patterns in a large data set, and to align these results with structural annotations from their domain. We provide data for the tool to analyze specific hidden state properties on dataset containing nesting, phrase structure, and chord progressions, and demonstrate how the tool can be used to isolate patterns for further statistical analysis.
http://lstm.seas.harvard.edu/
#harvard #video #dl #rnn
Google purchased scene segmentation technology.
https://techcrunch.com/2017/08/16/google-acquires-aimatter-maker-of-the-fabby-computer-vision-app/
#dl #segmentation #cv #google
DeepMind is pushing the boundaries to build better game AI. Python bindings are available.
https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/
#rl #deepmind #blizzard #python
Research group at MIT discovered new way of tracking sleep phase. WiFi can interfere, but they used deep learning to clear the signal and to achieve 80% accuracy in sleep stage prediction, compapable with a lab equipment.
http://news.mit.edu/2017/new-ai-algorithm-monitors-sleep-radio-waves-0807
#timeseries #eeg #deep_learning #mit #sleep
https://www.wired.com/story/googles-new-algorithm-perfects-photos-before-you-even-take-them/
#cv #photoes
https://twitter.com/odsai_en/status/888741521893335040
Читать полностью…Russian Search Engine has opened sources of the CatBoost — library which claims to be replacement of Yandex’s famous MatrixNet. Researches claim that CatBoost results are comparable with XGboost.
https://techcrunch.com/2017/07/18/yandex-open-sources-catboost-a-gradient-boosting-machine-learning-librar/
#opensource #yandex #xgboost #catboost