🎥 [part4]|Python Crash Course|Python for Data Science and Machine Learning Bootcamp
👁 1 раз ⏳ 5059 сек.
Python for Data Science and Machine Learning Bootcamp

Learn how to use NumPy, Pandas, Seaborn , Matplotlib , Plotly , Scikit-Learn , Machine Learning, Tensorflow , and more!

#python #Data #science #ml #machinelearning #datascience

What you'll learn!

Use Python for Data Science and Machine Learning

Use Spark for Big Data Analysis

Implement Machine Learning Algorithms

Learn to use NumPy for Numerical Data

Learn to use Pandas for Data Analysis

Learn to use Matplotlib for Python Plotting

Learn to use

​Causal Inference that’s not A/B Testing: Theory & Practical Guide

🔗 Causal Inference that’s not A/B Testing: Theory & Practical Guide
How to establish causality when you can’t run A/B tests? 5 methods to choose from, with theory, industry application and code examples.

🎥 Save costs training on AMLCompute
👁 1 раз ⏳ 952 сек.
With ever changing data and customer signals continuous training and retraining can incur higher costs, especially on GPUs for deep learning models. In AzureML, we have heard this concern loud and clear, and we want to share some tips to manage your costs and spend your budget wisely. Come learn about the latest updates to AMLcompute including some tips on saving costs.

00:40 - Introduction
03:22- Demo of enterprise ready features of AMLcompute
10:40- Demo of saving costs on AMLcompute

Learn More:
What is

🎥 The JerusML Show 19 - Yoav Levine (HUJI) - Deep learning and many-body quantum physics
👁 1 раз ⏳ 1164 сек.
Yoav Levine talking about Deep learning and many-body quantum physics: fundamental connections and bidirectional contributions as part of the JerusML Show, the first-ever Jerusalem Centered AI conference organized by JerusML, the largest professional tech community in Jerusalem.

JerusML is the AI and Data Science community of Jerusalem. With over 3000 members, JerusML is the largest professional community in Jerusalem.
JerusML main goal is to establish Jerusalem as a leading and thriving AI center in Israe

​Surprise Video With Our New Paper! - Photorealistic Material Editing 🔮

🔗 Surprise Video With Our New Paper! - Photorealistic Material Editing 🔮
📝 Our paper "Photorealistic Material Editing Through Direct Image Manipulation" and its source code are now available here: https://users.cg.tuwien.ac.at/zsolnai/gfx/photorealistic-material-editing/ ❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Anastasia Marchenkova, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn,

🎥 [part5]|Python for Data Analysis - NumPy|Python for Data Science and Machine Learning Bootcamp
👁 1 раз ⏳ 3782 сек.
Python for Data Science and Machine Learning Bootcamp

Learn how to use NumPy, Pandas, Seaborn , Matplotlib , Plotly , Scikit-Learn , Machine Learning, Tensorflow , and more!

#python #Data #science #ml #machinelearning #datascience

What you'll learn!

Use Python for Data Science and Machine Learning

Use Spark for Big Data Analysis

Implement Machine Learning Algorithms

Learn to use NumPy for Numerical Data

Learn to use Pandas for Data Analysis

Learn to use Matplotlib for Python Plotting

Learn to use

​Качество кода Apache Hadoop: production VS test

Для того, чтобы получить качественный production код, недостаточно просто обеспечить максимальное покрытие тестами. Несомненно, для того, чтобы добиться высоких результатов, основной код проекта и тесты обязаны работать в идеально сплоченном тандеме. Поэтому уделять внимания тестам нужно столько же, сколько и основному коду. Написание хорошего теста – залог того, что он отловит регрессию в production. Чтобы показать важность того, что баги в тестах ничем не хуже, чем в production, рассмотрим очередной разбор предупреждений статического анализатора PVS-Studio. Цель: Apache Hadoop.

🔗 Качество кода Apache Hadoop: production VS test
Для того, чтобы получить качественный production код, недостаточно просто обеспечить максимальное покрытие тестами. Несомненно, для того, чтобы добиться высоких...

​Развитие компилятора C для нового мультиклета-нейропроцессора

На конференции разработчиков системного и инструментального ПО – OS DAY 2016, которая прошла в г. Иннополис 9-10 июня 2016 (Казань) при обсуждении доклада о мультиклеточной архитектуре была высказана мысль, что она будет наиболее эффективной при решении задач искусственного интеллекта. Условия для разработки нового процессора общего назначения, ориентированного на задачи ИИ, сложились в текущем году.

Нейропроцессор Мультиклет S2, проект которого был впервые представлен на Huawei Innovation Forum 2019 является дальнейшим развитием мультиклеточной архитектуры. От ранее созданных мультиклетов он отличается системой команд, а именно вводом новых типов малоразмерных данных (с фиксированной и плавающей запятой) и операций с ними. Увеличено количество клеток – 256 и частота – 2,5 ГГц, что должно обеспечить пиковую производительность 81,9 TФлопс на 16F и, соответственно, сделать его сравнимым, в части нейровычислений, с возможностями современных специализированных ASIC TPU (TPU-3: 90 Тфлопс на 16F).

Так как эффективность использования процессоров в значительной мере зависит от оптимальности компилятора разработана развиваемая схема оптимизации кода.
Рассмотрим ее более подробно.

🔗 Развитие компилятора C для нового мультиклета-нейропроцессора
На конференции разработчиков системного и инструментального ПО – OS DAY 2016, которая прошла в г. Иннополис 9-10 июня 2016 (Казань) при обсуждении доклада о му...

​Pandas Tips & Tricks: Need For Speed

🔗 Pandas Tips & Tricks: Need For Speed
A Personal Favorite 1-Liner

​The year in AI: 2019 ML/AI advances recap

🔗 The year in AI: 2019 ML/AI advances recap
It has become somewhat of a tradition for me to do an end-of-year retrospective of advances in AI/ML (see last year’s round up for…

​Kaggle Reading Group: On NMT Search Errors and Model Errors: Cat Got Your Tongue? (Part 2) | Kaggle

🔗 Kaggle Reading Group: On NMT Search Errors and Model Errors: Cat Got Your Tongue? (Part 2) | Kaggle
This week we'll be continuing "On NMT Search Errors and Model Errors: Cat Got Your Tongue?" by Felix Stahlber and Bill Byrne, published at EMNLP 2019. You can follow along with the paper here: https://www.aclweb.org/anthology/D19-1331.pdf About Kaggle: Kaggle is the world's largest community of data scientists. Join us to compete, collaborate, learn, and do your data science work. Kaggle's platform is the fastest way to get started on a new data science project. Spin up a Jupyter notebook with a single cli

🎥 Microsoft Cognitive Service to Add Image and Voice Intelligence to your apps
👁 1 раз ⏳ 3564 сек.
Cognitive Services is a set of APIs that use the power of Machine Learning to enhance your application. Using these APIs, you can quickly add image recognition and analysis , speech recognition , text-to-speech capabilities , and many other features to your application.
In this presentation, you will learn about the capabilities of these APIs, how to test them, and how to call them via a REST web service and using some helpful .NET libraries.

This channel is all about latest trending technologies tutoria

​Demystifying the Confusion Matrix

🔗 Demystifying the Confusion Matrix
Not nearly as confusing as the name implies!

🎥 Fuzzy Logic in Artificial Intelligence | Introduction to Fuzzy Logic & Membership Function | Edureka
👁 2 раз ⏳ 1168 сек.
***AI and Deep Learning using TensorFlow: https://www.edureka.co/ai-deep-learning-with-tensorflow ***
This Edureka Live video on "Fuzzy Logic in AI" will explain what is fuzzy logic and how it is used to find different possibilities between 0 and 1. It also explains the architecture of this logic along with real-time examples.
(blog: https://www.edureka.co/blog/fuzzy-logic-ai/ )

-----------------------------------------------------------

Machine Learning Podcast - http://bit.ly/2IGLYCc
Complete Yout

​Named Entity Disambiguation Boosted with Knowledge Graphs

🔗 Named Entity Disambiguation Boosted with Knowledge Graphs
We combine text and graph based approaches to build a Named Entity Disambiguation pipeline.

🎥 Introduction and Logistics Advance AI Deep Reinforcement Learning Python (Part1)
👁 2 раз ⏳ 1280 сек.
Hello Everyone, How Are You ?
Today i'll share video about Advance AI Deep Reinforcement Learning Python (Part 1)


Part :
1. Introduction and Outline
2. Where to get the Code
3. Tensor Flow


Please support us with subscribe this channel
Thank You


#artificialintelligence #Python

​TensorFlow 2 Tutorial: Get Started in Deep Learning With tf.keras

🔗 TensorFlow 2 Tutorial: Get Started in Deep Learning With tf.keras
Predictive modeling with deep learning is a skill that modern developers need to know. TensorFlow is the premier open-source deep learning framework developed and maintained by Google. Although using TensorFlow directly can be challenging, the modern tf.keras API beings the simplicity and ease of use of Keras to the TensorFlow project. Using tf.keras allows you …

​Objective Video Quality Analysis at Airtime

🔗 Objective Video Quality Analysis at Airtime
by Caitlin O’Callaghan

​Comparing the Effects of Annotation Type on Machine Learning Detection Performance http://openaccess.thecvf.com/content_CVPRW_2019/html/PBVS/Mullen_Comparing_the_Effects_of_Annotation_Type_on_Machine_Learning_Detection_CVPRW_2019_paper.html

🔗 CVPR 2019 Open Access Repository

​What is My Data Worth? – The Berkeley Artificial Intelligence

https://bair.berkeley.edu/blog/2019/12/16/data-worth/

🔗 What is My Data Worth?
The BAIR Blog