​New version of our open STT dataset - 0.5, now in beta

https://github.com/snakers4/open_stt/releases/tag/v0.5-beta

🔗 snakers4/open_stt
Russian open STT dataset. Contribute to snakers4/open_stt development by creating an account on GitHub.

​Deploying Models to Flask

🔗 Deploying Models to Flask
A walk-through on how to deploy machine learning models for user interaction using Python and Flask

​The XIV Meltdown

🔗 The XIV Meltdown
Why a “Sure Bet” Turned Into an Epic Financial Meltdown

​Deep (Learning+Random) Forest и разбор статей

Конференции
Продолжаем рассказывать про конференцию по статистике и машинному обучению AISTATS 2019. В этом посте разберем статьи про глубокие модели из ансамблей деревьев, mix регуляризацию для сильно разреженных данных и эффективную по времени аппроксимацию кросс-валидации.
https://habr.com/ru/company/ru_mts/blog/458388/

🔗 Deep (Learning+Random) Forest и разбор статей
Продолжаем рассказывать про конференцию по статистике и машинному обучению AISTATS 2019. В этом посте разберем статьи про глубокие модели из ансамблей деревьев,...

​AI, Truth, and Society: Deepfakes at the front of the Technological Cold War

🔗 AI, Truth, and Society: Deepfakes at the front of the Technological Cold War
Developments, implications, and strategies

​25 Open Datasets for Deep Learning
https://www.analyticsvidhya.com/blog/2018/03/comprehensive-collection-deep-learning-datasets/

🔗 25 Open Datasets for Deep Learning Every Data Scientist Must Work With
Introduction The key to getting better at deep learning (or most fields in life) is practice. Practice on a variety of problems – from image processing to speech recognition. Each of these problem has it’s own unique nuance and approach. But where can you get this data? A lot of research papers you see

​Database Normalization Explained

🔗 Database Normalization Explained
Learn about database normalization by designing and modifying an example database schema!

​Next Level Art and the Future of Work and Leisure

🔗 Next Level Art and the Future of Work and Leisure
Becoming More Creative (and Human) with AI

🎥 A Gentle Introduction to Machine Learning and React Native - React Native - June 2019
👁 1 раз ⏳ 1261 сек.
Presented by Valentin Nagacevschi

A gentle introduction to AI and Machine Learning and how to make them work together in your React Native app. We will cover some common patterns and will also touch on the latest Apple CoreML technologies.

_

About Pusher Sessions:

We're bringing the meetup to you. With Sessions, you can watch recordings of top-notch talks from developer meetups -- wherever and whenever you want.

Meetups are a great way to learn from our peers and to keep up with the latest trends and t

🎥 Introduction to Machine Learning with TensorFlow.js - JSConf.Asia 2019
👁 1 раз ⏳ 10998 сек.
Speaker: Asim Hussain @jawache

Learn how to build and train Neural Networks using the most popular Machine Learning framework for JavaScript, TensorFlow.js. This is a practical workshop where you'll learn "hands-on" by building several different applications from scratch using TensorFlow.js. If you have ever been interested in Machine Learning, if you want to get a taste for what this exciting field has to offer, if you want to be able to talk to other Machine Learning/AI specialists in a language they und

​Погружение в свёрточные нейронные сети. Часть 5 / 10 — 18

🔗 Погружение в свёрточные нейронные сети. Часть 5 / 10 — 18
Полный курс на русском языке можно найти по этой ссылке. Оригинальный курс на английском доступен по этой ссылке. Выход новых лекций запланирован каждые 2-3 дня...

​Using ML for holiday planning: Summarising Airbnb reviews

🔗 Using ML for holiday planning: Summarising Airbnb reviews
When it comes to holiday accommodation, Airbnb is the first avenue that immediately comes to mind.

​Распознавание источников освещения на картах окружения
#Python

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
В этой статье представлена реализация на Python алгоритма распознавания источников освещения на картах окружения (LDR или HDR) при помощи равнопромежуточной проекции (equirectangular projection). Однако после внесения незначительных изменений её также можно использовать с простыми фоновыми изображениями или кубическими картами. Примеры возможного применения алгоритма: программы трассировки лучей, в которых требуется распознавать первичные источники освещения для испускания из них лучей; в растеризованных рендерерах он может применяться для отбрасывания теней, использующих карту окружения; кроме того, алгоритм также можно применять в программах устранения засветов, например в AR.
https://habr.com/ru/post/458598/

🔗 Распознавание источников освещения на картах окружения
В этой статье представлена реализация на Python алгоритма распознавания источников освещения на картах окружения (LDR или HDR) при помощи равнопромежуточной про...

​Глупые мозги, скрытые эмоции, коварные алгоритмы: эволюция распознавания лиц

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Древние египтяне знали толк в вивисекции и могли на ощупь отличить печень от почки. Пеленая с утра до вечера мумии и занимаясь врачеванием (от трепанации до удаления опухолей), поневоле научишься разбираться в анатомии.

Богатство анатомических подробностей с лихвой компенсировалось неразберихой с пониманием функции органов. Жрецы, врачи и простой люд смело помещали разум в сердце, а мозгу отводили роль производителя слизи для носа.

Спустя 4 тыс. лет трудно позволить себе смеяться над феллахами и фараонами — наши компьютеры и алгоритмы сбора данных выглядят круче, чем папирусные свитки, а мозг все так же загадочно производит не пойми что.

Вот и в данной статье предполагалось рассказать о том, что алгоритмы распознавания эмоций достигли скорости зеркальных нейронов в интерпретации сигналов собеседника, как вдруг выяснилось, что нервные клетки стали не тем, чем кажутся.
https://habr.com/ru/company/ivideon/blog/458666/

🔗 Глупые мозги, скрытые эмоции, коварные алгоритмы: эволюция распознавания лиц
Древние египтяне знали толк в вивисекции и могли на ощупь отличить печень от почки. Пеленая с утра до вечера мумии и занимаясь врачеванием (от трепанации до уд...

​Optimistic Bull or Pessimistic Bear: Adaptive Deep Reinforcement Learning for Stock Portfolio Allocation

Authors: Xinyi Li, Yinchuan Li, Yuancheng Zhan, Xiao-Yang Liu

Abstract: is crucial for investment companies. However, getting the best strategy in a complex and dynamic stock market is challenging. In this paper, we propose a novel Adaptive Deep Deterministic Reinforcementhttps://arxiv.org/abs/1907.01503

🔗 Optimistic Bull or Pessimistic Bear: Adaptive Deep Reinforcement Learning for Stock Portfolio Alloca
Portfolio allocation is crucial for investment companies. However, getting the best strategy in a complex and dynamic stock market is challenging. In this paper, we propose a novel Adaptive Deep Deterministic Reinforcement Learning scheme (Adaptive DDPG) for the portfolio allocation task, which incorporates optimistic or pessimistic deep reinforcement learning that is reflected in the influence from prediction errors. Dow Jones 30 component stocks are selected as our trading stocks and their daily prices are used as the training and testing data. We train the Adaptive DDPG agent and obtain a trading strategy. The Adaptive DDPG's performance is compared with the vanilla DDPG, Dow Jones Industrial Average index and the traditional min-variance and mean-variance portfolio allocation strategies. Adaptive DDPG outperforms the baselines in terms of the investment return and the Sharpe ratio.

​Artificial Intelligence && Deep Learning

🔗 Artificial Intelligence && Deep Learning
666 Free Online Programming & Computer Science Courses You Can Start This July join👇👇👇 @DeepLearning_AI .https://www.freecodecamp.org/news/free-coding-courses-july-2019/

​Method of diagnosing heart disease based on deep learning ECG signal

Authors: Jie Zhang, Bohao Li, Kexin Xiang, Xuegang Shi

Abstract: …signal by heart disease type. However, the currency is not so sufficient that it can be used in medical applications. We develop an algorithm that combines signal processing and deep learning to classify ECG signals into Normal AF other rhythm and noise, which help us solve this problem.
https://arxiv.org/abs/1907.01514

🔗 Method of diagnosing heart disease based on deep learning ECG signal
The traditional method of diagnosing heart disease on ECG signal is artificial observation. Some have tried to combine expertise and signal processing to classify ECG signal by heart disease type. However, the currency is not so sufficient that it can be used in medical applications. We develop an algorithm that combines signal processing and deep learning to classify ECG signals into Normal AF other rhythm and noise, which help us solve this problem. It is demonstrated that we can obtain the time-frequency diagram of ECG signal by wavelet transform, and use DNN to classify the time-frequency diagram to find out the heart disease that the signal collector may have. Overall, an accuracy of 94 percent is achieved on the validation set. According to the evaluation criteria of PhysioNet/Computing in Cardiology (CinC) in 2017, the F1 score of this method is 0.957, which is higher than the first place in the competition in 2017.

🎥 Webinar - Customer Analytics using Machine Learning | Great Learning
👁 1 раз ⏳ 4558 сек.
Customer Analytics plays a significant role in studying data of customers behavior to make key business decisions. According to reports, 67% of consumers list bad experience as one of the primary reasons for churning, many just shun the option of going back to the same place to avail services based on bad experience and 85% would warn others about doing business with the company. This majorly impacts the business scenario and hence customer analytics plays a significant role in learning about customer behav

🎥 Face Generation with nVidia StyleGAN and Python (7.3)
👁 1 раз ⏳ 627 сек.
It can take considerable training effort and compute time to build a face generating GAN from scrarch. nVidia StyleGAN offers pretrained weights and a TensorFlow compatible wrapper that allows you to generate realistic faces out of the box. StyleGAN does require a GPU, however, Google CoLab GPU works just fine, as this video demonstrates.

Code for This Video:
https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class04_training.ipynb
Course Homepage: https://sites.wustl.edu/jeffheaton

​Serving Prophet Model with Flask — Predicting Future

🔗 Serving Prophet Model with Flask — Predicting Future
The solution to demonstrate how to serve Prophet model API on the Web with Flask. Prophet — Open-Source Python library developed by…