Principal components analysis
https://www.neuraldesigner.com/blog/principal-components-analysis
https://www.neuraldesigner.com/blog/principal-components-analysis
Neuraldesigner
Understanding principal components analysis (PCA) | Neural Designer
Principal component analysis allows us to reduce the size of a data set without much loss of information. Read this blog to learn how to do it !
Карта артистов, неуклюжий поиск связей в данных и как можно изобрести велосипед
https://habrahabr.ru/post/329250/
https://habrahabr.ru/post/329250/
Хабр
Карта артистов, неуклюжий поиск связей в данных и как можно изобрести велосипед
Недавно смотрел серию видео популяризатора математики. Там он пытается рассказывать про математический анализ и линейную алгебру немного с позиции человека, кото...
Нас окружают огромные объемы информации в виде текстов, и часто нам нужно уметь их обрабатывать. Хотите узнать как?
2 июня приглашаем на онлайн-курс «Введение в обработку естественного языка» от преподавателя Уральского федерального университета Павла Браславского. Это первый русскоязычный курс по этой теме, он создан с учётом специфики русского языка и познакомит вас и с базовыми лингвистическими инструментами, и с популярными приложениями обработки естественного языка.
Не пропустите: https://stepik.org/1233.
2 июня приглашаем на онлайн-курс «Введение в обработку естественного языка» от преподавателя Уральского федерального университета Павла Браславского. Это первый русскоязычный курс по этой теме, он создан с учётом специфики русского языка и познакомит вас и с базовыми лингвистическими инструментами, и с популярными приложениями обработки естественного языка.
Не пропустите: https://stepik.org/1233.
Stepik: online education
Введение в обработку естественного языка
Курс знакомит слушателей с основными концепциями, методами, инструментами и приложениями дисциплины "Обработка естественного языка" (Natural Language Processing)
Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI
http://alexgkendall.com/computer_vision/bayesian_deep_learning_for_safe_ai/
http://alexgkendall.com/computer_vision/bayesian_deep_learning_for_safe_ai/
Home
Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI
Bayesian Deep Learning, Computer Vision, Uncertainty
Automated deep neural network design via genetic programming
https://github.com/joeddav/devol
https://github.com/joeddav/devol
GitHub
GitHub - joeddav/devol: Genetic neural architecture search with Keras
Genetic neural architecture search with Keras. Contribute to joeddav/devol development by creating an account on GitHub.
The Machine Intelligence Behind Gboard
https://research.googleblog.com/2017/05/the-machine-intelligence-behind-gboard.html
https://research.googleblog.com/2017/05/the-machine-intelligence-behind-gboard.html
Research Blog
The Machine Intelligence Behind Gboard
Posted by Françoise Beaufays, Principal Scientist, Speech and Keyboard Team and Michael Riley, Principal Scientist, Speech and Languages Alg...
ICML 2017 Accepted Papers
https://2017.icml.cc/Conferences/2017/AcceptedPapersInitial
https://2017.icml.cc/Conferences/2017/AcceptedPapersInitial
Semi-supervised learning in python using pomegranate
https://github.com/jmschrei/pomegranate/blob/master/tutorials/Tutorial_8_Semisupervised_Learning.ipynb
https://github.com/jmschrei/pomegranate/blob/master/tutorials/Tutorial_8_Semisupervised_Learning.ipynb
GitHub
jmschrei/pomegranate
pomegranate - Fast, flexible and easy to use probabilistic modelling in Python.
Numerai’s New Tournament to Crowdsource the Future of the Stock Market
https://medium.com/numerai/numerais-new-tournament-to-crowdsource-the-future-of-the-stock-market-da1ac02adaef
https://medium.com/numerai/numerais-new-tournament-to-crowdsource-the-future-of-the-stock-market-da1ac02adaef
Medium
Numerai’s New Tournament to Crowdsource the Future of the Stock Market
The traditional crowdsourced machine learning tournament depends on a holdout dataset. The holdout data is some historical data known to…
Deep Voice 2: Multi-Speaker Neural Text-to-Speech
http://research.baidu.com/deep-voice-2-multi-speaker-neural-text-speech/
http://research.baidu.com/deep-voice-2-multi-speaker-neural-text-speech/
Everything that Works Works Because it's Bayesian: Why Deep Nets Generalize?
http://www.inference.vc/everything-that-works-works-because-its-bayesian-2/
http://www.inference.vc/everything-that-works-works-because-its-bayesian-2/
inFERENCe
Everything that Works Works Because it's Bayesian: Why Deep Nets Generalize?
The Bayesian community should really start going to ICLR. They really should
have started going years ago. Some people actually have.
For too long we Bayesians have, quite arrogantly, dismissed deep neural networks
as unprincipled, dumb black boxes that…
have started going years ago. Some people actually have.
For too long we Bayesians have, quite arrogantly, dismissed deep neural networks
as unprincipled, dumb black boxes that…
OpenAI Baselines: DQN
https://blog.openai.com/openai-baselines-dqn/
https://blog.openai.com/openai-baselines-dqn/
Intel открывает доступ к clDNN [высокопроизводительной библиотеке для глубокого обучения]
https://habrahabr.ru/company/1cloud/blog/329474/?utm_source=vk&utm_medium=social&utm_campaign=intel-otkryvaet-dostup-k-cldnn-%5Bvysokopr
https://habrahabr.ru/company/1cloud/blog/329474/?utm_source=vk&utm_medium=social&utm_campaign=intel-otkryvaet-dostup-k-cldnn-%5Bvysokopr
habrahabr.ru
Intel открывает доступ к clDNN [высокопроизводительной библиотеке для глубокого обучения]
Официальный репозиторий проекта был запущен буквально пару дней назад. Расскажем немного подробнее об этой новости и приведем полезные источники по теме. /...
A practical explanation of a Naive Bayes classifier
https://monkeylearn.com/blog/practical-explanation-naive-bayes-classifier/
https://monkeylearn.com/blog/practical-explanation-naive-bayes-classifier/
MonkeyLearn Blog
A practical explanation of a Naive Bayes classifier
Naive Bayes is a family of simple but powerful machine learning algorithms that use probabilities and Bayes’ Theorem to predict the category of a text.
NIPS 2016: A survey of tutorials, papers, and workshops
https://www.twosigma.com/insights/nips-2016-a-survey-of-tutorials-papers-and-workshops-two-sigma
https://www.twosigma.com/insights/nips-2016-a-survey-of-tutorials-papers-and-workshops-two-sigma
Two Sigma
NIPS 2016: A survey of tutorials, papers, and workshops | Two Sigma
Two Sigma researchers discuss notable advances in deep learning, optimization algorithms, Bayesian techniques, and time-series analysis presented at 2016's Conference on Neural Information Processing Systems (NIPS).
Using Empirical Bayes to approximate posteriors for large "black box" estimators
http://www.unofficialgoogledatascience.com/2015/11/using-empirical-bayes-to-approximate.html
http://www.unofficialgoogledatascience.com/2015/11/using-empirical-bayes-to-approximate.html
Unofficialgoogledatascience
Using Empirical Bayes to approximate posteriors for large "black box" estimators
by OMKAR MURALIDHARAN Many machine learning applications have some kind of regression at their core, so understanding large-scale regressi...
COMMON REPRESENTATION LEARNING USING DEEP CORRNET
https://deeplearn.school.blog/2017/05/24/common-representation-learning-using-deep-corrnet/
https://deeplearn.school.blog/2017/05/24/common-representation-learning-using-deep-corrnet/
Deep learn
Common Representation Learning using Deep CorrNet
In this post, I am going to discuss Deep CorrNet that is described in Correlational Neural Network which is a Common Representation Learning (CRL) technique. I have implemented CorrNet in Python us…