​Как сделать свой автоскейлер для кластера
Привет! Мы обучаем людей работе с большими данными. Невозможно себе представить образовательную программу по большим данным без своего кластера, на котором все участники совместно работают. По этой причине на нашей программе он всегда есть :) Мы занимаемся его настройкой, тюнингом и администрированием, а ребята непосредственно запускают там MapReduce-джобы и пользуются Spark'ом.
В этом посте мы расскажем, как мы решали проблему неравномерной загрузки кластера, написав свой автоскейлер, используя облако Mail.ru Cloud Solutions.

🔗 Как сделать свой автоскейлер для кластера
Привет! Мы обучаем людей работе с большими данными. Невозможно себе представить образовательную программу по большим данным без своего кластера, на котором все у...

​Джедайская техника уменьшения сверточных сетей — pruning

Перед тобой снова задача детектирования объектов. Приоритет — скорость работы при приемлемой точности. Берешь архитектуру YOLOv3 и дообучаешь. Точность(mAp75) больше 0.95. Но скорость прогона всё еще низкая. Черт.
Сегодня обойдём стороной квантизацию. А под катом рассмотрим Model Pruning — обрезание избыточных частей сети для ускорения Inference без потери точности. Наглядно — откуда, сколько и как можно вырезать. Разберем, как сделать это вручную и где можно автоматизировать. В конце — репозиторий на keras.

🔗 Джедайская техника уменьшения сверточных сетей — pruning
Перед тобой снова задача детектирования объектов. Приоритет — скорость работы при приемлемой точности. Берешь архитектуру YOLOv3 и дообучаешь. Точность(mAp75) б...

​PyTorch/TPU MNIST Demo
https://colab.research.google.com/drive/1mxhxqg1rQEFwcEAqjtKZLzwtFlQaO44V#scrollTo=Afwo4H7kSd8P

🔗 Google Colaboratory

​Можно ли применять искусственный интеллект для приема на работу и расчета заработной платы?

https://bigdata-madesimple.com/artificial-intelligence-in-hr-and-payroll-embracing-disruption/

🔗 Artificial intelligence in HR and Payroll: Disruptions in human resources
Artificial intelligence applications are developing rapidly – and businesses are waking up to the potential of the technology in HR and payroll.

​Rachael's Farewell Stream | Kaggle

🔗 Rachael's Farewell Stream | Kaggle
Rachael will be leaving Kaggle for new opportunities in the new year, so please join her for her final live stream on the Kaggle channel where she'll go over some of her favorite notebooks from her time here. 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 click. Build with our huge reposi

​Optimized Deep Q-learning for Automated Atari Space Invaders: An Implementation in Tensorflow 2.0.

🔗 Optimized Deep Q-learning for Automated Atari Space Invaders: An Implementation in Tensorflow 2.0.
Exploring the Importance of Data Preprocessing

​The future of Machine Learning

🔗 The future of Machine Learning
A look into the future of ML with Jeff Dean

​Why is Python Programming a perfect fit for Big Data?

🔗 Why is Python Programming a perfect fit for Big Data?
We’ll discuss in the blog the major benefits of using Python for big data.

🎥 Machine Learning: A New Approach to Drug Discovery with Daphne Koller - #332
👁 1 раз ⏳ 2621 сек.
Today we continue our 2019 NeurIPS coverage joined by Daphne Koller, co-Founder and former co-CEO of Coursera and Founder and CEO of Insitro. We caught up with Daphne to discuss:

Her background in machine learning, beginning in ‘93, and her work with the Stanford online machine learning courses, and eventually her work at Coursera. The current landscape of pharmaceutical drug discovery, including the current pricing of drugs and misnomers with why drugs are so expensive, Her work at Insitro, a compan

​One of the best Machine Learning Professors
Full series on ML by CalTech Prof. Yaser Abu-Mostafa
https://www.youtube.com/watch?v=idu8kaPFf1A&list=PL41qI9AD63BMXtmes0upOcPA5psKqVkgS

🔗 CalTech ML Course Lecture 01 - The Learning Problem
The Learning Problem - Introduction; supervised, unsupervised, and reinforcement learning. Components of the learning problem. Lecture 1 of 18 of Caltech's Machine Learning Course - CS 156 by Professor Yaser Abu-Mostafa. View course materials on the course website - http://work.caltech.edu/telecourse.html Produced in association with Caltech Academic Media Technologies under the Attribution-NonCommercial-NoDerivs Creative Commons License (CC BY-NC-ND). To learn more about this license, http://creativecommo

🎥 Decision Tree in Machine Learning | Great Learning Live Session
👁 1 раз ⏳ 4920 сек.
In this live session, we will take your through the concepts of decision tree machine learning algorithm and demonstrate in Python.

#DecisionTree #MachineLearning #GreatLearning
Agenda:
- Decision Tree Concepts
- Demo R/Python
- Finding Impurity of a Node
-- Entropy
-- Gini Index

- Great Learning has collaborated with the University of Texas at Austin for the PG Program in Artificial Intelligence and Machine Learning and with UT Austin McCombs School of Business for the PG Program in Analytics and Bu

​Top 7 Modern programming languages to learn now

🔗 Top 7 Modern programming languages to learn now
How Rust, Go, Kotlin, TypeScript, Swift, Dart, Julia can boost your career and improve your software development skills

​Introducing NVIDIA DRIVE AGX Orin: Vehicle Performance for the AI Era

https://blogs.nvidia.com/blog/2019/12/17/ai-baidu-alibaba-accelerate/

🔗 As AI Universe Keeps Expanding, NVIDIA CEO Lays Out Plan to Accelerate All of It | The Official NVID
With the AI revolution spreading across industries everywhere, NVIDIA founder and CEO Jensen Huang took the stage Wednesday to unveil the latest technology for speeding its mass adoption. His talk — to more than 6,000 scientists, engineers and entrepreneurs gathered for this week’s GPU Technology Conference in Suzhou, two hours west of Shanghai — touched Read article ?

🎥 How to make a neural network with tensorflow
👁 1 раз ⏳ 1161 сек.
How to quickly and easily make your first neural network. No setup or software install required. This code walkthrough uses Tensorflow and Keras layers.

There is lots more to learn like different loss functions, different activation functions, network architectures that belong in different videos.

You can jump right into the colab notebook here https://colab.research.google.com/drive/1eburtci3CUZrw-_Z-VhbNlrDxzrnFXFv

​Black Hole Machine Learning

🔗 Black Hole Machine Learning
Neural Networks vie Theoretical Physics

​Самые интересные применения машинного обучения в социальных сетях, маркетинге и другом в 2019 году.

https://www.geeksforgeeks.org/top-machine-learning-applications-in-2019/

🔗 Top Machine Learning Applications in 2019 - GeeksforGeeks
Suppose you want to search Machine Learning on Google. Well, the results you will see are carefully curated and ranked by Google using Machine Learning!!!… Read More »

🎥 Fields in Data Science | What are the different fields in data science?
👁 1 раз ⏳ 1140 сек.
In this video, you will understand the #Data #Science #Fields such as Mathematics, statistics, Machine Learning, Cluster Analysis, Data Mining, Big data Analytics, Data Visualization, Artificial Intelligence, Neural Networks, Deep Learning, Deep Active Learning, Cognitive Computing.

Get Data Science Training: https://www.besanttechnologies.com/training-courses/data-warehousing-training/datascience-training-institute-in-chennai

For Best Training and Certifications Contact Us Now!
📞 Classroom : +91 8099 770

​Advanced Google Skills for Data Science

🔗 Advanced Google Skills for Data Science
Optimize your programming by searching like a professional

​Multiple Linear Regression-Beginner’s Guide

🔗 Multiple Linear Regression-Beginner’s Guide
In this article i will be focusing on making a multiple linear regression model from scratch in python for beginners.

🎥 Fall 2019 Robotics Colloquium: Debadeepta Dey (Microsoft Research)
👁 1 раз ⏳ 3380 сек.
Lecture title: Imitation-Learning with Indirect Oracles

We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates a real-world scenario in that (a) the requester may not know how to navigate to the target objects and thus makes requests by only specifying high-level endgoals, and (b) the agent is capable of sensing when it is l