Tensorflow Machine Learning for Art and Music

🎥 Tensorflow Machine Learning for Art and Music
👁 1 раз ⏳ 585 сек.
In this video, I’ll share some of my favorite Tensorflow Magenta projects. The purpose of this video is to give you some ideas about how to learn Tensorflow and Machine Learning. If music or art inspire you to create, these are some great projects to get started.

I also share a visualization tool playground. This will help you better understand neural network in Tensorflow.

Here are the links to the projects
Visualize Neural Network - https://playground.tensorflow.org/
Tenserflow Magena Projects - https

Machine learning @ booking.com

🎥 Machine learning @ booking.com / Виктор Билык (booking.com)
👁 1 раз ⏳ 2634 сек.
HighLoad++ Siberia 2018

Зал «Красноярск», 25 июня, 16:00

Тезисы и презентация:
http://www.highload.ru/siberia/2018/abstracts/3608

В booking.com я занимаюсь созданием платформы для вывода в промышленную эксплуатацию продуктов машинного обучения.
Я расскажу о том, как устроена продуктовая разработка в booking.com и о месте машинного обучения в этом процессе. Покажу конкретные примеры применения моделей, расскажу о проблемах мониторинга их качественных характеристик и об архитектуре нашей (постоянно эволюц

​Investigating octopus camouflage with ICA and hierarchical clustering

https://towardsdatascience.com/investigating-octopus-camouflage-with-ica-and-hierarchical-clustering-df0e9a4ffaf4?source=collection_home---2------0---------------------

🔗 Investigating octopus camouflage with ICA and hierarchical clustering
How neuroscientists study this amazing skill with machine learning algorithms

​Interpreting the coefficients of linear regression

https://towardsdatascience.com/interpreting-the-coefficients-of-linear-regression-cc31d4c6f235?source=collection_home---4------4---------------------

🔗 Interpreting the coefficients of linear regression – Towards Data Science
Including transformations of variables

Playing Pong using Reinforcement Learning
https://towardsdatascience.com/intro-to-reinforcement-learning-pong-92a94aa0f84d?source=collection_home---4------2---------------------

Learning on non-Euclidean domains | Deep Learning on Computational Accelerators

🎥 Lecture 11 - Learning on non-Euclidean domains | Deep Learning on Computational Accelerators
👁 1 раз ⏳ 7687 сек.
Given by Prof. Alex Bronstein

https://habr.com/post/435984/

Нейросети и философия языка

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://yangx.top/ai_machinelearning_big_data

​Добрый день!

Приглашаем всех желающих принять участие в 3-ем всероссийском конкурсе русскоговорящих чат-бот в формате Теста Тьюринга, который будет проходить в рамках конференции по искусственному интеллекту Opentalks.ai! Море полезной и интересной информации от представителей науки и бизнеса, а также призы и веселье гарантированы!
Подробности конкурса и пройти регистрацию можно здесь http://opentalks.ai/ru/turing-test

🔗 OpenTalks.AI - Тест Тьюринга
OpenTalks.AI - Тест Тьюринга

Introduction to Deep learning

🎥 Introduction to Deep learning Lecture 1
👁 1 раз ⏳ 3655 сек.

​Deep learning in one medium: combining Code, Math and HTML. Open source book for everyone

http://d2l.ai/index.html

🔗 Dive into Deep Learning — Dive into Deep Learning documentation

​What is Deep Learning?

🔗 What is Deep Learning?
Let us understand what deep learning is. For more content on AI, Machine Learning, Data Sciences and Deep Learning, SUBSCRIBE and LIKE the video! REFERENCES ...

Linear Regression vs Logistic Regression | Data Science Training |

🎥 Linear Regression vs Logistic Regression | Data Science Training | Edureka
👁 1 раз ⏳ 1227 сек.
** Data Science Certification using R: https://www.edureka.co/data-science **
This Edureka video on Linear Regression Vs Logistic Regression covers the basic concepts of linear and logistic models. The following topics are covered in this session:
(01:05) Types of Machine Learning
(03:09) Regression Vs Classification
(05:47) What is Linear Regression?
(09:22) What is Logistic Regression?
(13:26) Linear Regression Use Case
(15:02) Logistic Regression Use Case
(16:18) Linear Regression Vs Logistic Regression

​How to Fix Vanishing Gradients Using the Rectified Linear Activation Function

https://machinelearningmastery.com/how-to-fix-vanishing-gradients-using-the-rectified-linear-activation-function/

🔗 How to Fix Vanishing Gradients Using the Rectified Linear Activation Function
The vanishing gradients problem is one example of unstable behavior that you may encounter when training a deep neural network. It describes the situation where a deep multilayer feed-forward network or a recurrent neural network is unable to propagate useful gradient information from the output end of the model back to the layers near the …

​Developing neural networks is often referred to as a dark art. The reason for this is that being skilled at developing neural network models comes from experience. There are no reliable methods to analytically calculate how to design a “good” or “best” model for your specific dataset

https://machinelearningmastery.com/books-for-deep-learning-practitioners/

🔗 Three Must-Own Books for Deep Learning Practitioners
Developing neural networks is often referred to as a dark art. The reason for this is that being skilled at developing neural network models comes from experience. There are no reliable methods to analytically calculate how to design a “good” or “best” model for your specific dataset. You must draw on experience and experiment in …

Deep Learning on Computational Accelerators

🎥 Tutorial 12 | Deep Learning on Computational Accelerators
👁 1 раз ⏳ 2516 сек.
Given by Prof. Alex Bronstein

​"Evolved NN topologies for different alphabet systems. Noticable: similar alphabets have similar topologies"
🔎 https://www.nature.com/articles/s42256-018-0006-z

🔗 Designing neural networks through neuroevolution
Deep neural networks have become very successful at certain machine learning tasks partly due to the widely adopted method of training called backpropagation. An alternative way to optimize neural networks is by using evolutionary algorithms, which, fuelled by the increase in computing power, offers a new range of capabilities and modes of learning.

Nikola Živković - Solving Real-World problem using machine learning in Python #growITconf

🎥 Nikola Živković - Solving Real-World problem using machine learning in Python #growITconf
👁 1 раз ⏳ 2733 сек.
Presentation: https://github.com/NMZivkovic/growit-machinelearning

Predict Bike Sharing demand in Washington using Python and Sci-Kit Learn.
At the moment machine learning is crossing the chasm, from early adopters to early majority. Even though concepts of this field can be traced back to the 50s, big breakthroughs have been made in the last five years.
Apart from that, there are many machine learning libraries available, especially for data science languages like Python and R. That is one of the reasons

Deep Learning course : to Machine Learning Based AI

🎥 Deep Learning 1: Introduction to Machine Learning Based AI
👁 1 раз ⏳ 6188 сек.


🎥 Deep Learning 2: Introduction to TensorFlow
👁 1 раз ⏳ 6411 сек.
Slides in video contain images from:
http://colah.github.io/about.html
http://colah.github.io/contact.html

🎥 Deep Learning 3: Neural Networks Foundations
👁 1 раз ⏳ 6276 сек.


🎥 Reinforcement Learning 1: Introduction to Reinforcement Learning
👁 1 раз ⏳ 6197 сек.


🎥 Reinforcement Learning 2: Exploration and Exploitation
👁 1 раз ⏳ 6504 сек.


🎥 Reinforcement Learning 3: Markov Decision Processes and Dynamic Programming
👁 1 раз ⏳ 6264 сек.


🎥 Reinforcement Learning 4: Model-Free Prediction and Control
👁 1 раз ⏳ 5966 сек.


🎥 Reinforcement Learning 5: Function Approximation and Deep Reinforcement Learning
👁 1 раз ⏳ 6296 сек.


🎥 Reinforcement Learning 6: Policy Gradients and Actor Critics
👁 1 раз ⏳ 5681 сек.


🎥 Deep Learning 5: Optimization for Machine Learning
👁 1 раз ⏳ 4510 сек.

🎥 Многорукие бандиты в рекомендациях / Михаил Каменщиков (Avito)
👁 1 раз ⏳ 1890 сек.
HighLoad++ Siberia 2018

Зал «Красноярск», 25 июня, 17:00

Тезисы и презентация:
http://www.highload.ru/siberia/2018/abstracts/3701

В Avito я занимаюсь Data Science и разработкой микросервисов в команде Recommendations.
Многорукие бандиты - это один из методов тестирования гипотез, который можно применять в качестве альтернативы A/B-тестированию. Главное отличие в том, что бандиты позволяют оптимизировать выигрыш сразу после начала эксперимента и делают это автоматически. У нас возникла задача тестировать

My Sweet Dreams about Automatic Sleep-Stage Classification
https://towardsdatascience.com/my-sweet-dreams-about-automatic-sleep-stage-classification-414128441728?source=collection_home---4------2---------------------