Евгений Разинков. Лекция 10. Кластеризация (курс "Машинное обучение, весна 2019)
https://www.youtube.com/watch?v=lEUTG6s5YhY

🎥 Евгений Разинков. Лекция 10. Кластеризация (курс "Машинное обучение, весна 2019)
👁 1 раз ⏳ 3608 сек.
Лекция посвящена алгоритмам кластеризации. Рассмотрены следующие вопросы:
- Постановка задачи кластеризации.
- Алгоритм k-means.
- Целевая функция алгоритма k-means.
- Вывод формул обновления весов из целевой функции.
- Агломеративная кластеризация.
- Способы вычисления расстояния между кластерами: Single-Link, Average-Link, Complete-Link.

Евгений Разинков -- к.ф.-м.н., руководитель отдела машинного обучения и компьютерного зрения Группы компаний FIX, ассистент кафедры системного анализа и ИТ института ВМи

​Awesome Machine Learning
A curated list of awesome machine learning frameworks, libraries and software (by language).

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
libraries: https://github.com/josephmisiti/awesome-machine-learning

books: https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md

🔗 josephmisiti/awesome-machine-learning
A curated list of awesome Machine Learning frameworks, libraries and software. - josephmisiti/awesome-machine-learning

​Data Science Simplified Part 12: Resampling Methods

🔗 Data Science Simplified Part 12: Resampling Methods
Concept

​Building a Vocal Emotion Sensor with Deep Learning
Teaching machines to better understand human communication

https://towardsdatascience.com/building-a-vocal-emotion-sensor-with-deep-learning-bedd3de8a4a9?source=topic_page---------------------------20

🔗 Building a Vocal Emotion Sensor with Deep Learning
Teaching machines to better understand human communication

🎥 17. Bayesian Statistics
👁 1 раз ⏳ 4685 сек.
MIT 18.650 Statistics for Applications, Fall 2016
View the complete course: http://ocw.mit.edu/18-650F16
Instructor: Philippe Rigollet

In this lecture, Prof. Rigollet talked about Bayesian approach, Bayes rule, posterior distribution, and non-informative priors.

License: Creative Commons BY-NC-SA
More information at http://ocw.mit.edu/terms
More courses at http://ocw.mit.edu

🎥 35. Finding Clusters in Graphs
👁 1 раз ⏳ 2089 сек.
MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018
Instructor: Gilbert Strang
View the complete course: https://ocw.mit.edu/18-065S18
YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63oMNUHXqIUcrkS2PivhN3k

The topic of this lecture is clustering for graphs, meaning finding sets of 'related' vertices in graphs. The challenge is finding good algorithms to optimize cluster quality. Professor Strang reviews some possibilities.

License: Creative

🎥 33. Neural Nets and the Learning Function
👁 1 раз ⏳ 3367 сек.
MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018
Instructor: Gilbert Strang
View the complete course: https://ocw.mit.edu/18-065S18
YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63oMNUHXqIUcrkS2PivhN3k

This lecture focuses on the construction of the learning function F, which is optimized by stochastic gradient descent and applied to the training data to minimize the loss. Professor Strang also begins his review of distance matrices.

Lic

​New State of the Art AI Optimizer: Rectified Adam (RAdam). Improve your AI accuracy instantly versus Adam, and why it works.

🔗 New State of the Art AI Optimizer: Rectified Adam (RAdam). Improve your AI accuracy instantly versus Adam, and why it works.
A new paper by Liu, Jian, He et al introduces RAdam, or “Rectified Adam”. It’s a new variation of the classic Adam optimizer that provides…

​PVS-Studio в гостях у Apache Hive

#BigData

Последние десять лет движение open source является одним из ключевых факторов развития IT-отрасли и важной ее составной частью. Роль и место open source не только усиливается в виде роста количественных показателей, но происходит и изменение его качественного позиционирования на IT-рынке в целом. Не сидя сложа руки, бравая команда PVS-Studio активно способствует закреплению позиций open source проектов, находя затаившиеся баги в огромных толщах кодовых баз и предлагая для таких проектов бесплатные лицензии. Эта статья не исключение! Сегодня речь пойдет об Apache Hive! Отчет получен — есть на что посмотреть!
https://habr.com/ru/company/pvs-studio/blog/463759/

🔗 PVS-Studio в гостях у Apache Hive
Последние десять лет движение open source является одним из ключевых факторов развития IT-отрасли и важной ее составной частью. Роль и место open source не толь...

​How to Deal with Imbalanced Data using SMOTE - Analytics Vidhya -

https://medium.com/analytics-vidhya/balance-your-data-using-smote-98e4d79fcddb

🔗 How to Deal with Imbalanced Data using SMOTE
With a Case Study in Python

​О чем не расскажешь на ML тренировке — Артур Кузин

🔗 О чем не расскажешь на ML тренировке — Артур Кузин
Артур Кузин рассказывает о том, о чём бы он не рассказал на ML тренировке (доклад секции Black ML, Data Fest⁶). Из видео вы сможете узнать различные истории из соревнований и хакатонов, из-за которых и родилась идея создание Black ML секции. Узнать о текущих соревнованиях можно на сайте http://mltrainings.ru/ Узнать о новых тренировках и видео можно из групп: ВКонтакте https://vk.com/mltrainings Facebook https://www.facebook.com/groups/1413405125598651/ Telegram https://xn--r1a.website/mltrainings

​Interpreting Latent Space of GANs for Semantic Face Editing

https://shenyujun.github.io/InterFaceGAN/

code: https://github.com/ShenYujun/InterFaceGAN.git

🔗 InterFaceGAN
InterFaceGAN.

​Elon Musk: What's Outside the Simulation? | AI Podcast Clips

🔗 Elon Musk: What's Outside the Simulation? | AI Podcast Clips
This is a clip from a conversation with Elon Musk on the Artificial Intelligence podcast. You can watch the full conversation here: http://bit.ly/2Z8vma4 If you enjoy these, consider subscribing, sharing, and commenting below. Full episode: http://bit.ly/2Z8vma4 Full episodes playlist: http://bit.ly/2EcbaKf Podcast website: https://lexfridman.com/ai Elon Musk is the CEO of Tesla, SpaceX, Neuralink, and a co-founder of several other companies. Subscribe to this YouTube channel or connect on: - Twitter: ht

​Everything you need to know about Tensorflow 2.0🔥
https://towardsdatascience.com/everything-you-need-to-know-about-tensorflow-2-0-b0856960c074

🔗 Everything you need to know about TensorFlow 2.0
Keras-APIs, SavedModels, TensorBoard, Keras-Tuner and more.

Realtime Deep Learning for Self-Driving Cars: Making the Mass Production of AVs Feasible

https://www.youtube.com/watch?v=vpWpvPizv8c

🎥 Realtime Deep Learning for Self-Driving Cars: Making the Mass Production of AVs Feasible
👁 1 раз ⏳ 1393 сек.
- While deep learning was originally designed for powerful processors (e.g., NVIDIA GPUs), efficient processors must be used in order to apply deep learning on the edge, which is crucial for self-driving cars.
- Limitations of software optimization, algorithm optimization, and post processing
- Running accurate deep learning algorithms on low power processors to significantly reduce cost and improve accuracy on powerful processors

Speaker: Dr Amir Alush – Co-Founder and Chief Technology Officer, Brodmann17

​DEPLOYING A SEQ2SEQ MODEL WITH TORCHSCRIPT
Author: Matthew Inkawhich 1.2, this tutorial was updated to work with PyTorch 1.2

This tutorial will walk through the process of transitioning a sequence-to-sequence model to TorchScript using the TorchScript API. The model that we will convert is the chatbot model from the Chatbot tutorial. You can either treat this tutorial as a “Part 2” to the Chatbot tutorial and deploy your own pretrained model, or you can start with this document and use a pretrained model that we host. In the latter case, you can reference the original Chatbot tutorial for details regarding data preprocessing, model theory and definition, and model training.

https://pytorch.org/tutorials/beginner/deploy_seq2seq_hybrid_frontend_tutorial.html

🔗 Deploying a Seq2Seq Model with TorchScript — PyTorch Tutorials 1.2.0 documentation

🎥 Python Flappy Bird AI Tutorial (with NEAT) - Finishing the Graphics
👁 1 раз ⏳ 713 сек.
In this python flappy bird tutorial we finish creating the graphics for our game and fine tune a few features we worked on previously. In the next video we will start to implement the NEAT algorithm to build an AI that can play our flappy bird game.

Image Download: https://techwithtim.net/wp-content/uploads/2019/08/imgs.zip
Code Download: https://github.com/techwithtim/NEAT-Flappy-Bird

Enroll in The Fundamentals of Programming w/ Python
https://tech-with-tim.teachable.com/p/the-fundamentals-of-programmin

Keras Tuner - автоматическая оптимизация гиперпараметров нейросети | Нейросети на Python

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🎥 Keras Tuner - автоматическая оптимизация гиперпараметров нейросети | Нейросети на Python
👁 1 раз ⏳ 1076 сек.
Демонстрация использования Keras Tuner для подбора гиперпараметров нейронной сети, которые обеспечивают лучшее качество работы.
Курс "Программирование нейросетей на Python" - https://www.asozykin.ru/courses/nnpython

Keras Tuner - https://github.com/keras-team/keras-tuner/

Ноутбук в Colab, который используется в видео - https://colab.research.google.com/drive/1m_8puwuGg9C7LWChv4YvZEmAlocGC7nG

Как можно поддержать курс:
1. Яндекс Кошелек - https://money.yandex.ru/to/410014298228017
2. PayPal - https://www

​S&P 500 Stock Price Prediction Using Machine Learning and Deep Learning

🔗 S&P 500 Stock Price Prediction Using Machine Learning and Deep Learning
Time Series Forecasting methods including Simple Moving Average, Linear Regression, k-Nearest Neighbors, Auto ARIMA, Prophet, Long Short…

​AI Powered Search for Extra-terrestrial Intelligence — Analyzing Radio Telescopic Data
Visualizing Radio-Telescope Signal Data from SETI
https://towardsdatascience.com/ai-powered-search-for-extra-terrestrial-intelligence-analyzing-radio-telescopic-data-c9e46741041?source=collection_home---4------1-----------------------

🔗 AI Powered Search for Extra-terrestrial Intelligence — Analyzing Radio Telescopic Data
Visualizing Radio-Telescope Signal Data from SETI