​Why UMAP is Superior over tSNE

🔗 Why UMAP is Superior over tSNE
Does initialization really matter?

​ML for Optimization Problems | Qingchen Wang | Kaggle Days

🔗 ML for Optimization Problems | Qingchen Wang | Kaggle Days
Kaggle Days China edition was held on October 19-20 at Damei Center, Beijing. More than 400 data scientists and enthusiasts gathered to learn, make friends, and compete in a full-day offline competition. Kaggle Days is produced by LogicAI and Kaggle. About LogicAI: LogicAI is a boutique Data Science consultancy company owned by Kaggle fans and Grandmasters. As a global company, they do custom end-to-end AI and Data Science development projects as well as trainings for C-level management and tech teams.

​"Extreme Relative Pose Network under Hybrid Representations"

https://github.com/SimingYan/Hybrid_Relative_Pose

Article: https://arxiv.org/abs/1912.11695

🔗 SimingYan/Hybrid_Relative_Pose
Implementation of Paper "Extreme Relative Pose Network under Hybrid Representations" - SimingYan/Hybrid_Relative_Pose

​Machine Learning with Spark

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

📝 Pentreath - Machine Learning with Spark.pdf - 💾4 909 606

​Tensorflow — A deep learning framework

🔗 Tensorflow — A deep learning framework
Learn and do hands-on Tensorflow and get prepped to solve big problems

🎥 Story of Alan Turing Prize Winner Yoshua Bengio
👁 1 раз ⏳ 1560 сек.
Yoshua Bengio OC FRSC is a Canadian computer scientist, most noted for his work on artificial neural networks and deep learning. He was a co-recipient of the 2018 ACM A.M. Turing Award for his work in deep learning



Please Share , Like and Subscribe the channel to support our work .

Find us on facebook
https://www.facebook.com/hemchandralive

Our YouTube URL
https://www.youtube.com/c/hemchandralive

​Macaw: A conversational bot that enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration

https://www.profillic.com/paper/arxiv:1912.08904

🔗 Macaw: An Extensible Conversational Information Seeking Platform: Model and Code - Profillic
Click To Get Model/Code. Conversational information seeking (CIS) has been recognized as a major emerging research area in information retrieval. Such research will require data and tools, to allow the implementation and study of conversational systems. This paper introduces Macaw, an open-source framework with a modular architecture for CIS research. Macaw supports multi-turn, multi-modal, and mixed-initiative interactions, and enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration. It has a modular design to encourage the study of new CIS algorithms, which can be evaluated in batch mode. It can also integrate with a user interface, which allows user studies and data collection in an interactive mode, where the back end can be fully algorithmic or a wizard of oz setup. Macaw is distributed under the MIT License.

​Теория вероятности. Математическая статистика.
Лекция 1. Основные понятия теории вероятности
Лекция 2. Случайные величины и их характеристики
Лекция 3. Статистические гипотезы. Динамика процессов
Лекция 4. Направления теории случайных процессов
Лекция 5. Марковские случайные процессы
Лекция 6. Теория массового обслуживания
Лекция 7. Прогнозирование случайных процесов
#video #math
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Открыть в Telegram



🎥 Untitled
👁 1 раз ⏳ 5289 сек.


🎥 Untitled
👁 1 раз ⏳ 5370 сек.


🎥 Untitled
👁 1 раз ⏳ 5399 сек.


🎥 Untitled
👁 1 раз ⏳ 5181 сек.


🎥 Untitled
👁 1 раз ⏳ 5260 сек.


🎥 Untitled
👁 1 раз ⏳ 5394 сек.


🎥 Untitled
👁 1 раз ⏳ 5325 сек.

​Robot development with Jupyter
Wolf Vollprecht : https://medium.com/@wolfv/robot-development-with-jupyter-ddae16d4e688

🔗 Robot development with Jupyter
This post shows available tools to build browser based, advanced visualizations in Jupyter Notebooks for ROS and standalone web apps using

🎥 Christof Koch: The Future of Consciousness - Schrödinger at 75: The Future of Biology
👁 1 раз ⏳ 2884 сек.
Koch joined the Allen Institute as Chief Scientific Officer in 2011 and became President in 2015. He received his baccalaureate from the Lycée Descartes in Rabat, Morocco, his MSc in physics from the University of Tübingen in Germany and his PhD from the Max-Planck-Institut für Biologische Kybernetik, Tübingen. Subsequently, he spent four years as a postdoctoral fellow in the Artificial Intelligence Laboratory and the Brain and Cognitive Sciences Department at the Massachusetts Institute of Technology. From

🎥 Face editing with Generative Adversarial Networks
👁 4 раз ⏳ 1527 сек.
Link to Notebooks:
https://drive.google.com/open?id=1LBWcmnUPoHDeaYlRiHokGyjywIdyhAQb

Link to the StyleGAN paper: https://arxiv.org/abs/1812.04948

Link to GAN blogpost: http://hunterheidenreich.com/blog/gan-objective-functions/

If you want to support this channel, here is my patreon link:
https://patreon.com/ArxivInsights --- You are amazing!! ;)

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

This episode covers one of the greatest ideas in Deep Learning of the past couple of years: Generative Adversarial Networks.

​What or Why in Machine Learning

🔗 What or Why in Machine Learning
A comprehensive guide to interpreting models using Python

🎥 Курс "Машинное обучение в R, Python и H2O". Модуль 1. Предподготовка данных (10-я лекция)
👁 2 раз ⏳ 2795 сек.
Поддержать канал:
Webmoney R362258289857
PayPal pilapi@yandex.ru
II. Знакомство с Python
II.7. scikit-learn
II.7.6. Наиболее часто используемые классы и функции
II.7.6.8. Написание собственных классов для применения в конвейере
II.7.6.9. Модификация классов библиотеки scikit-learn для работы с датафреймами

III. Знакомство с R
III.1. Загрузка данных
III.2. Предварительная подготовка данных
III.3. Построение модели и работа с прогнозами
III.4. Перекрестная проверка и комбинированная проверка
для подбо

🎥 DSC Podcast Series: Selecting an Enterprise Deep Learning System
👁 1 раз ⏳ 1008 сек.
Selecting an Enterprise Deep Learning System

Every organization wants to infuse the power of AI in its business. In this first of two parts, we’ll explore the journey from development to production deep learning. Learn how to enable an end-to-end workflow that’s optimized for the rigors of deep learning in an enterprise setting, with predictable performance as your neural network models and datasets grow.

Speaker: Tony Paikeday, Director of Product Marketing for Deep Learning Systems -- Nvidia

Hosted by

​Deep Mining: Detecting Anomalous Patterns in Neural Network Activations with Subset Scanning

https://github.com/hikayifix/adversarialdetector

https://openreview.net/forum?id=Skld1aVtPB

🔗 hikayifix/adversarialdetector
Deep Mining: Detecting Anomalous Patterns in Neural Network Activations with Subset Scanning - hikayifix/adversarialdetector

​Deep Learning Models
A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.
By Sebastian Raschka : https://github.com/rasbt/deeplearning-models
#ArtificialIntelligence #DeepLearning #MachineLearning

🔗 rasbt/deeplearning-models
A collection of various deep learning architectures, models, and tips - rasbt/deeplearning-models

Подборка книг по машинному обучению🎯

1- Введение в машинное обучение с помощью Python. Руководство для специалистов по работе с данными (А. Мюллер, С. Гвидо)
https://tgme.pro/bfbook/1047

2- Крупномасштабное машинное обучение вместе с Python
(Бастиан Шарден, Лука Массарон, Альберто Боскетти)
https://tgme.pro/BookPython/259

3- Математические основы машинного обучения и прогнозирования
(Вьюгин В.В.)
https://tgme.pro/bfbook/967

4- Прикладной анализ текстовых данных на Python. Машинное обучение и создание приложений обработки естественного языка
(Бенгфорт Бенджамин, Билбро Ребекка, Охеда Тони)
https://tgme.pro/bfbook/945

5- Машинное обучение
(Хенрик Бринк, Джозеф Ричардс, Марк Феверолф)
https://tgme.pro/bfbook/700

6- Глубокое обучение на Python
(Франсуа Шолле)
https://tgme.pro/BookPython/99

7- Python и машинное обучение
(Рашка С.)
https://tgme.pro/BookPython/37

8- Глубокое обучение. Погружение в мир нейронных сетей
(С. Николенко, А. Кадурин, Е. Архангельская)
https://tgme.pro/bfbook/589

#book #MachineLearning

​Could Lab-Grown Brains Develop Consciousness?

https://singularityhub.com/2019/07/03/could-lab-grown-brains-develop-consciousness/

🔗 Could Lab-Grown Brains Develop Consciousness?
A week after transplant, the dissected neural clusters spontaneously formed multiple networks, and the team found synchronized waves throughout the network.

​Machine Learning 2020 - The Year of MI

Part 1 - Machine Learning For Beginners - Basics

https://youtu.be/E3l_aeGjkeI

Part 2 - MI environment

https://youtu.be/HqyrqxyDwPU

Part 3 - Python Decision Tree (Theory)

https://youtu.be/8isUCINSmys

Part 4 - Python Decision Tree (Coding)

https://youtu.be/24mxQzd3EsU

Part 5 - Python Decision Tree (Graphiviz)

https://youtu.be/aVEfKRfWjHc

Part 6 - Knn(Friend Recommender)

https://youtu.be/LK0zgA6Mr6k

Part 7- 5-Fold Cross Validation

https://youtu.be/Zx5cz8pXnOM

🔗 Machine Learning Tutorial Part 1 | Machine Learning For Beginners
This Machine Learning tutorial will introduce you to the different areas of Machine Learning and Artificial Intelligence. In this part of the course you will learn about the three different learning types (Unsupervised learning, Supervised Learning and Reinforcement Learning) For more see: https://www.Vinsloev.com Remember to Subscribe to the channel to see the upcoming parts of this Tutorial as well.