🎥 Deep Learning на пальцах 8 - Metric Learning, Autoencoders, GANs
👁 24 раз ⏳ 5622 сек.
Курс: http://dlcourse.ai
Слайды: https://www.dropbox.com/s/n25eai8ivlq60bh/Lecture%208%20-%20Metric%20and%20Unsupervised.pdf?dl=0

​Time Series Feature Extraction for industrial big data (IIoT) applications

🔗 Time Series Feature Extraction for industrial big data (IIoT) applications
Feature Extraction by Distributed and Parallel means for industrial big data applications

🎥 What's New in TensorFlow, and How GCP Developers Benefit (Cloud Next '19)
👁 1 раз ⏳ 2368 сек.
TensorFlow 2.0 has landed!

During this session, you will learn all about TensorFlow 2.0's new features, usability enhancements, and performance increases - many of which are specifically optimized for cloud platforms.

We will use the TF2.0 migration tool to transition a model from TensorFlow 1.x to 2.0, and deploy an end-to-end machine learning model to Google Cloud Platform.

If you're interested in using TensorFlow for your deep learning experiments on GCP, you won't want to miss this talk!

Big Data An

​Multi-Class Text Classification with LSTM

🔗 Multi-Class Text Classification with LSTM
How to develop LSTM recurrent neural network models for text classification problems in Python using Keras deep learning library

🎥 GOTO 2018 • Augmented Reality and Machine Learning Cooperation on Mobile • Mourad Sidky
👁 1 раз ⏳ 2087 сек.
This presentation was recorded at GOTO Copenhagen 2018. #gotocon #gotocph
http://gotocph.com

Mourad Sidky - iOS Tech Lead at Groupon

ABSTRACT
Mobile devices are getting more and more powerful, with not-only advanced hardware, but also intelligent operating systems and high-performance compatible set of native frameworks. Mobile devices are capable of doing expensive on-device processing to achieve augmented reality and machine learning, without the need to communicate to any other external services.
Apple

🎥 Deep Dive into Machine Learning in ArcGIS Platform
👁 1 раз ⏳ 15932 сек.
In this hands-on workshop, you will be exposed to machine learning in the ArcGIS Platform (Pro and Online), in addition to Python integration to leverage powerful machine learning and deep learning libraries. You will learn advanced use patterns and best practices for machine learning tools in ArcGIS Pro, in addition to best practices for integrating external machine learning libraries. After this workshop you will be equipped with:
- Workflows for setting up a machine learning environment in your computer

​The Power of A/B Testing

🔗 The Power of A/B Testing
A visual summary of how sample size, effect size and significance level affect the power of A/B testing

​Generalizable Deep Reinforcement Learning

🔗 Generalizable Deep Reinforcement Learning
What Google AI’s PlaNet AI means for reinforcement learning research and how transfer learning plays a key role

​Насколько точно Яндекс прогнозирует осадки зимой? Анализируем точность прогностических сервисов

🔗 Насколько точно Яндекс прогнозирует осадки зимой? Анализируем точность прогностических сервисов
В ноябре я публиковал статью «Яндекс.Метеум – технология без технологии. Маркетинг с точностью до района», где соотносил качество прогнозов Яндекса с другими сер...

​Step Change Improvement in Molecular Property Prediction with PotentialNet

🔗 Step Change Improvement in Molecular Property Prediction with PotentialNet
TL;DR: Pande Lab in collaboration with Merck shows marked increase in ADMET Prediction accuracy with PotentialNet

🎥 TensorFlow 2.0 - Introductory Tutorial
👁 3 раз ⏳ 588 сек.
TensorFlow 2.0 is here! Let's take a look at a simple tutorial on the basics of TensorFlow.

The code is available at the GitHub repository for the series:

If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer those.

If you enjoy these tutorials & would like to support them then the easiest way is to simply like the video & give it a thumbs up & also it's a huge help to share these videos with anyone who you think wou

​ВАКАНСИЯ В ВК!!!
ОПЛАТА ЕЖЕДНЕВНО, СДЕЛЬНО-ПОЧАСОВАЯ:
1ЧАС-500Р
2ЧАСА-1000Р
3ЧАСА-1500Р
4ЧАСА-2000Р
ВСЕ ВОПРОСЫ К ЕКАТЕРИНЕ

​Unsupervised Learning | DeepMind

🔗 Unsupervised Learning | DeepMind
Unsupervised learning is a paradigm designed to create autonomous intelligence by rewarding computer programs for learning about the data they observe without a particular task in mind--in other words, the program learns for the sake of learning. We believe unsupervised learning will be foundational to building artificial general intelligence.

🎥 Product Innovation Keynote (Cloud Next '19)
👁 1 раз ⏳ 6252 сек.
Hear about Google Cloud's latest solution innovations across security, infrastructure, Maps, data analytics, ML & AI, G Suite, and more.

Accelerating Machine Learning App Development → https://bit.ly/2TZfO60

Next ‘19 All Sessions playlist → https://bit.ly/Next19AllSessions

Subscribe to the GCP Channel → https://bit.ly/GCloudPlatform


Speaker(s): Justin Arbuckle, Michael Heim, Urs Hölzle, Thomas Kurian, Amy Lokey, , Binu Mathew,
Moderator: Sarah Patterson
Panelists: Rajen Sheth, Karen Van Kirk

Session

​Reviewing Python Visualization Packages

🔗 Reviewing Python Visualization Packages
Which solutions are good in which situations?

​Introducing LinkedIn’s Avro2TF

🔗 Introducing LinkedIn’s Avro2TF
A New Feature Transformation Framework for TensorFlow

​Vaex: A DataFrame with super-strings

🔗 Vaex: A DataFrame with super-strings
Speed up your text processing up to a 1000x

🎥 GitHub and Deep Learning on Graphs of Code - Clair Sullivan, GitHub
👁 1 раз ⏳ 1011 сек.
GitHub is presently hosts approximately 0.5 PB of data on open source code. These data include the code itself and the various contributions to it, such as commits, pull requests, issues, comments, and users. A great deal of information can be learned about code and the open source community that creates it.

KEY TAKEAWAYS
- How can graphs of code be used to obtain information about software and open source development?
- What are appropriate methods for deep learning on such graphs?
- Best-in-class methods

🎥 Introduction to Deep Learning 4 8 19
👁 1 раз ⏳ 4855 сек.

​🔗