​Использование кастомных функций потери и метрики качества обучения в Keras
При обучении нейронной сети на обучающей выборке на выходе нейросети вычисляются два ключевых параметра эффективности обучения — ошибка и точность предсказания. Для этого используются функция потери (loss) и метрика точности. Эти метрики различаются в зависимости от поставленной задачи (классификация или сегментация изображения, детекция объекта, регрессия). В Keras мы можем определить свои собственные функцию потери и метрики точности под свою конкретную задачу. О таких кастомных функциях и пойдет речь в статье. Кому интересно, прошу под кат.

🔗 Использование кастомных функций потери и метрики качества обучения в Keras
При обучении нейронной сети на обучающей выборке на выходе нейросети вычисляются два ключевых параметра эффективности обучения — ошибка и точность предсказания.

​Speeding Through Dates with Pandas

🔗 Speeding Through Dates with Pandas
Methods for increasing the speed of DateTime conversions by ? 480X.

​Implementing YOLO on a custom dataset

🔗 Implementing YOLO on a custom dataset
In this article we will learn step by step implementation of YOLO v2 using keras on a custom data set and some common issues and their…

​The Cardio of Audio

🔗 The Cardio of Audio
Scrutinizing the Audio Data in Data Science

​How to publish a Jupyter notebook online — using AWS in 10 minutes!

🔗 How to publish a Jupyter notebook online — using AWS in 10 minutes!
A great way to build a data science portfolio or share notebooks with others!

🎥 Art + AI - Pittsburgh ML Summit ‘19
👁 1 раз ⏳ 1468 сек.
Victor Dibia, ML Research Engineer at Cloudera Fast Forward Labs, talks about what he does as GDE both at work and for the community. He combines his love of art using Generative Adversarial Networks. Join us and see how these two roads intersect.

Beyond Big Data: AI/ML Summit is a unique opportunity for managers on every level to learn more about the opportunities of these technologies, while connecting with others in the industry. With a focus on trends and best practices, the event aims to explore strat

​How to Build a Reusable NLP Code Pipeline with Scikit-Learn

🔗 How to Build a Reusable NLP Code Pipeline with Scikit-Learn
With an Emphasis on Feature Engineering and Training

​Бот-философ для vk.com
По мотивам многих статей, которые были посвящены ботоводам…

Недавно разрабатывал «под ключ» один интересный проект, посвященный соц.сети vk.com. Задача проста — создать бота, которого можно будет добавить в беседу и который будет выдавать случайные цитаты. Но это показалось слишком просто, поэтому пришлось возродить великого философа Фридриха Ницше, который сделает из бота — сверхбота…

🔗 Бот-философ для vk.com
По мотивам многих статей, которые были посвящены ботоводам… Недавно разрабатывал «под ключ» один интересный проект, посвященный соц.сети vk.com. Задача проста —...

​Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers

https://locuslab.github.io/2019-10-28-cvxpylayers/

🔗 Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers

​What can artificial intelligence do for physics? And what will it do to physics?

https://backreaction.blogspot.com/2019/11/what-can-artificial-intelligence-do-for.html

🔗 What can artificial intelligence do for physics? And what will it do ?i?to?/i? physics?
Science News, Physics, Science, Philosophy, Philosophy of Science

​How to Ensure Data Integrity in Analytical Systems

🔗 How to Ensure Data Integrity in Analytical Systems
A look at data integrity, lifecycle, and security in computerized analytical systems

🎥 What is Reinforcement Learning and how to train machine
👁 1 раз ⏳ 1205 сек.
Reinforcement learning is the training of machine learning models to make a sequence of decisions. Watch Mr. Mainak Sen, Director, Business Brio unveils about Reinforcement Learning.

​Bayesian Deep Learning - NeurIPS 2019 Workshop

http://bayesiandeeplearning.org

🔗 Bayesian Deep Learning Workshop | NeurIPS 2019
Bayesian Deep Learning Workshop at NeurIPS 2019 — Friday, December 13, 2019 — Vancouver Convention Center, Vancouver, Canada.

​Deep Learning in mobile and wireless networking:

https://arxiv.org/pdf/1803.04311.pdf

https://jisajournal.springeropen.com/articles/10.1186/s13174-018-0087-2/

🔗 A comprehensive survey on machine learning for networking: evolution, applications and research oppo
Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this s

​How to Make Computers Dream

🔗 How to Make Computers Dream
A soft introduction to Generative Models

​"Latent ODEs for Irregularly-Sampled Time Series"

GitHub: https://github.com/YuliaRubanova/latent_ode/

https://arxiv.org/abs/1907.03907

#MachineLearning #OrdinaryDifferentialEquations #TimeSeries

🔗 YuliaRubanova/latent_ode
Code for "Latent ODEs for Irregularly-Sampled Time Series" paper - YuliaRubanova/latent_ode

​Visualization Library in Python: Matplotlib

🔗 Visualization Library in Python: Matplotlib
In my previous story, I’ve described two of the most important Python libraries in python: Numpy and Pandas. Today I’ll narrate Matplotlib…

​Прикладной анализ текстовых данных на Python. Машинное обучение

📝 Applied Deep Learning with Python Use scikit-learn, TensorFlow, and Keras to create intelligent systems and machine learning... - 💾35 586 419

📝 Прикладной анализ текстовых данных на Python. Машинное обучение и создание приложений обработки естественного языка [2019] Бе.. - 💾10 802 107