​Review: SENet — Squeeze-and-Excitation Network, Winner of ILSVRC 2017 (Image Classification)

🔗 Review: SENet — Squeeze-and-Excitation Network, Winner of ILSVRC 2017 (Image Classification)
With SE Blocks, Surpasses ResNet, Inception-v4, PolyNet, ResNeXt, MobileNetV1, DenseNet, PyramidNet, DPN, ShuffleNet V1

🎥 Train Custom Machine Learning Models with No Data Science Expertise (Google I/O'19)
👁 1 раз ⏳ 1315 сек.
Cloud AutoML is a suite of machine learning products that enables developers with limited machine learning expertise to train high-quality models specific to their needs, by leveraging Google’s state-of-the-art neural architecture search technology. Learn the power and ease-of-use of Cloud AutoML Tables, Video Intelligence, and Natural Language, and take a look at how Cloud AutoML would fare if it were to participate in data science competitions.

Watch more #io19 here:
GCP at Google I/O 2019 Playlist → ht

🎥 Machine Learning is the New Chicken Sexer - This Week in Google 507
👁 1 раз ⏳ 7351 сек.
Google I/O Highlights
This Week's Stories

--  Google I/O Highlights
--  Pixel 3A Unboxing
--  Nest Hub Max > Google Home Hub
--  AR Walking Directions in Google Maps
--  Google Leans into Helpfulness vs Privacy
--  Project Euphonia: Speech-to-text for People who are Hard to Understand
--  Trouble in Chromebook Land
--  AR Coming to Google Search
--  Next-Generation Google Assistant
--  Changes to Android Auto
--  Assistant Speeds Up
--  Google Maps Gets Incognito Mode
--  Android Q Preview
--  Protest Plan

🎥 ML Kit: Machine Learning for Mobile with Firebase (Google I/O'19)
👁 1 раз ⏳ 2284 сек.
ML Kit allows you to harness the power of machine learning in your iOS and Android apps without needing to be an expert in it. Leverage powerful, but simple-to-use on-device and cloud-based APIs for Vision and Natural Language Processing, or train and/or deploy your own models. Understand some big additions to ML Kit and how to use these to enable smarter, richer experiences to your users.

Watch more #io19 here:
Firebase at Google I/O 2019 Playlist → https://goo.gle/2GSFVqN
Google I/O 2019 All Sessions Pl

​My First Usage of Natural Language Processing (NLP) in Industry

🔗 My First Usage of Natural Language Processing (NLP) in Industry
People hear a lot about how fantastic NLP is, but often for many it can be hard to see how it can be applied in a commercial setting. With…

​Comparison of Activation Functions for Deep Neural Networks

🔗 Comparison of Activation Functions for Deep Neural Networks
Activation functions play a key role in neural networks, so it is essential to understand the advantages and disadvantages to achieve…

​Key differences between Artificial Intelligence and Machine Learning

🔗 Key differences between Artificial Intelligence and Machine Learning
ML uses the experience to look for the pattern it learned. AI uses the experience to acquire knowledge/skill and also how to apply that.

🎥 Deep Learning with TensorFlow - Introduction to TensorFlow
👁 1 раз ⏳ 1106 сек.
Welcome to second tutorial. Until now, we have used numpy to build neural networks. Now I will step you through a deep learning framework that will allow you to build neural networks more easily. Machine learning frameworks like TensorFlow can speed up your machine learning development significantly. This frameworks have a lot of documentation, which you should feel free to read. In this tutorial, I will teach to do the following in TensorFlow:
- Initialize variables
- Start your own session

Text version t

Deep Learning to Solve Challenging Problems (Google I/O'19)

https://www.youtube.com/watch?v=rP8CGyDbxBY

🎥 Deep Learning to Solve Challenging Problems (Google I/O'19)
👁 1 раз ⏳ 2459 сек.
This talk will highlight some of Google Brain’s research and computer systems with an eye toward how it can be used to solve challenging problems, and will relate them to the National Academy of Engineering's Grand Engineering Challenges for the 21st Century, including the use of machine learning for healthcare, robotics, and engineering the tools of scientific discovery. He will also cover how machine learning is transforming many aspects of our computing hardware and software systems.

Watch more #io19

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data
https://towardsdatascience.com/the-remarkable-world-of-recommender-systems-bff4b9cbe6a7?source=collection_home---4------2---------------------

🔗 The Remarkable world of Recommender Systems
An overview of the Recommendation systems and how they provide an effective form of targeted marketing.

​Breaking Into Data Science in 2019

🔗 Breaking Into Data Science in 2019
Insights from my journey from business into data science

🎥 ML Kit x Material Design: Design Patterns for Mobile Machine Learning (Google I/O'19)
👁 1 раз ⏳ 2043 сек.
Learn how to design user experiences for machine learning features in mobile apps using ML Kit and Material Design. This session will showcase design patterns for specific ML Kit API’s along with general considerations when designing for ML.

Watch more #io19 here:
Design at Google I/O 2019 Playlist → https://goo.gle/2IUneqd
Google I/O 2019 All Sessions Playlist → https://goo.gle/io19allsessions
Learn more on the I/O Website → https://google.com/io

Subscribe to the Google Design Channel → https://goo.gle

​TCAV: Interpretability Beyond Feature Attribution

🔗 TCAV: Interpretability Beyond Feature Attribution
An overview of GoogleAI’s model Interpretability technique in terms of human-friendly concepts.

Телочки показывают себя на камеру абсолютно бесплатно!
vk.com/wall-182157631_1

​Задача по #DataScience от QIWI.

Наверняка вы знаете, что такое Терминалы QIWI. Они позволяют совершить оплату в пользу более чем двух тысяч провайдеров. Сейчас пользователи мало платят через терминалы, не знают или не помнят, что их услугу можно оплатить на терминале.

QIWI ищет команду, которая сможет доработать (уже реализованный) механизм, рекомендующий плательщику дополнительный платёж. Нужно научиться определять наиболее уместных провайдеров для данного терминала, исходя из его локации и частоты оплачиваемых провайдеров.

На реализацию QIWI выделяет 3 млн.рублей и 5 месяцев.

Задача подробно описана на сайте (видео + текст) — universe.qiwi.com

Заявки от команд до 19 мая.

🔗 QIWI Universe Product Hub 2019 — Сделаем бизнес вместе!
Product Hub QIWI Universe 3.0 2019

​Implementing SPADE using fastai

🔗 Implementing SPADE using fastai
I was fascinated by the results of Nvidia’s latest research paper when it came out. If you haven’t looked at the paper result then you are…

🎥 Diagnostic Visualization for Machine Learning with YellowBrick w/ Rebecca Bilbro - TWiML Talk #264
👁 1 раз ⏳ 2559 сек.
Today we close out our PyDataSci series joined by Rebecca Bilbro, head of data science at ICX media and co-creator of the popular open-source visualization library YellowBrick.

In our conversation, Rebecca details:

• Her relationship with toolmaking, which led to the eventual creation of Yellowbrick.

• Popular tools within YellowBrick, including a summary of their unit testing approach.

• Interesting use cases that she’s seen over time.

• The growth she’s seen in the community of contrib

🎥 Towards demystifying over-parameterization in deep (...) - Soltanolkotabi - Workshop 3 - CEB T1 2019
👁 1 раз ⏳ 2627 сек.
Mahdi Soltanolkotabi (USC) / 04.04.2019

Towards demystifying over-parameterization in deep learning.

Many modern learning models including deep neural networks are trained in an over-parameterized regime where the parameters of the model exceed the size of the training dataset. Training these models involve highly non-convex landscapes and it is not clear how methods such as (stochastic) gradient descent provably find globally optimal models. Furthermore, due to their over-parameterized nature these neur

​6 июля в Минске пройдет конференция AI MEN 2019. AI MEN 2019 – это международная конференция по использованию технологий искусственного интеллекта (ИИ), Data Science, Machine Learning, Big Data.

Вход бесплатный по предварительной регистрации!

🔗 AI-MEN 2019
AI-MEN 2019 - международная конференция по Artificial intelligence, Data Science и Machine Learning, 6 июля 2019 г., гостиница "Виктория", Минск

🎥 Learned image reconstruction for high-resolution (...) - Betcke - Workshop 3 - CEB T1 2019
👁 1 раз ⏳ 2611 сек.
Marta Betcke (University College London) / 05.04.2019

Learned image reconstruction for high-resolution tomographic imaging.

Recent advances in deep learning for tomographic reconstructions have shown a great promise to create accurate and high quality images from subsampled measurements in a time considerably shorter than needed by the established nonlinear regularisation methods such as e.g. TV. This new paradigm also offers a new implicit way of expressing prior knowledge through training on a class of