​LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands and Water from Aerial Imagery

For project and dataset: https://www.catalyzex.com/paper/arxiv:2005.02264

🔗 LandCover.ai

​Finding patterns with rules

🔗 Finding patterns with rules
Concepts and examples

​Enabling E-Textile Microinteractions: Gestures and Light through Helical Structures">
Enabling E-Textile Microinteractions: Gestures and Light through Helical Structures

🔗 Enabling E-Textile Microinteractions: Gestures and Light through Helical Structures
Posted by Alex Olwal, Research Scientist, Google Research Textiles have the potential to help technology blend into our everyday environ...

​Romulus: A Case Study for Understanding Concurrency & Elastic Range Locks

🔗 Romulus: A Case Study for Understanding Concurrency & Elastic Range Locks
Going beyond one-dimensional, serial programs and exploiting a multi-core world

​Tutorial: Network Visualization Basics with Networkx and Plotly in Python

🔗 Tutorial: Network Visualization Basics with Networkx and Plotly in Python
From a Shakespeare script to a visually dynamic network graph

🎥 KNN Algorithm in Machine Learning using Python from Scratch - Jupyter Python Machine Learning Course
👁 1 раз ⏳ 1159 сек.
This is the video tutorial#08 for Artificial Intelligence complete course from beginner to advanced level.

In this video you will learn about k nearest neighbour algorithm in machine learning and you will also learn how to implement k nearest neighbour algorithm in python with movies examples.

If anyone wants to support us, then please become a patreon: https://www.patreon.com/user/posts?u=22962224

Our other Channel, Please Subscribe: https://www.youtube.com/channel/UC44PcIfCeVGA21fbL_-qd9Q

Link to our

​The Enterprise Big Data Lake
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Открыть в Telegram



📝 The Enterprise Big Data Lake Delivering the Promise of Big Data and Data Science by Alex Gorelik (z-lib.org).pdf - 💾11 027 598

​Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis

https://nv-adlr.github.io/Flowtron/

https://arxiv.org/abs/2005.05957

🔗 Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opinion scores (MOS) show that Flowtron matches state-of-the-art TTS models in terms of speech quality. In addition, we provide results on control of speech variation, interpolation between samples and style transfer between speakers seen and unseen during training. Code and pre-trained models will be made publicly available at https://github.com/NVIDIA/flowtron

Jim Keller - Moore's Law in the age of AI Chips
https://www.youtube.com/watch?v=8eT1jaHmlx8

🎥 Jim Keller - Moore's Law in the age of AI Chips
👁 1 раз ⏳ 1866 сек.
For more talks and to view corresponding slides, go to scaledml.org, select [media archive].

Presented at the 5th Annual Scaled Machine Learning Conference 2020
Venue: Computer History Museum

scaledml.org | #scaledml2020

​Count people in webcam using pre-trained YOLOv3

🔗 Count people in webcam using pre-trained YOLOv3
Learn to use instance segmentation (YOLOv3) to count the number of people using its pre-trained weights with TensorFlow and OpenCV in…

курс "Вычисления на видеокартах"
введение в OpenCL

полный курс -https://www.youtube.com/playlist?list=PLlb7e2G7aSpTgwAm0GBkvn5XA0NokovJJ
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🎥 Лекция 1. История видеокарт, введение в OpenCL (Вычисления на видеокартах)
👁 1 раз ⏳ 5031 сек.
Лекция №1 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: https://bit.ly/2CK3IdP

🎥 Лекция 2. Введение в OpenCL. Архитектура видеокарты (Вычисления на видеокартах)
👁 1 раз ⏳ 4335 сек.
Лекция №2 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: https://bit.ly/2Ow3dW9

🎥 Лекция 3. Примеры оптимизаций с local memory (Вычисления на видеокартах)
👁 1 раз ⏳ 4948 сек.
Лекция №3 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: https://bit.ly/2IdkyAH

🎥 Лекция 4. Умножение матриц (Вычисления на видеокартах)
👁 1 раз ⏳ 5134 сек.
Лекция №4 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: https://bit.ly/2zMsJS2

🎥 Лекция 5. Collision detection (Вычисления на видеокартах)
👁 1 раз ⏳ 4110 сек.
Лекция №5 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: https://bit.ly/2Ns1Ne1

🎥 Лекция 6. Сортировки и collision detection 2 (Вычисления на видеокартах)
👁 1 раз ⏳ 4108 сек.
Лекция №6 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: ht...

🎥 Лекция 7. Merge sort и Semi-Global Matching (Вычисления на видеокартах)
👁 1 раз ⏳ 4575 сек.
Лекция №7 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: ht...

🎥 Лекция 8. Sparse matrices, poisson reconstruction, LUT (Вычисления на видеокартах)
👁 1 раз ⏳ 5739 сек.
Лекция № 8 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: ...

🎥 Самая лучшая лекция: вариационные методы (Вычисления на видеокартах)
👁 1 раз ⏳ 5105 сек.
Variational methods:

Image denoising via Total Variation Minimization:
TV-L2 (ROF)
TV-L1
Image Super Resolution:
TV-L1
Huber model
2.5D surface re...

🎥 Лекция 10. Растеризация: OpenGL, Larrabee, cudaraster (Вычисления на видеокартах)
👁 1 раз ⏳ 5410 сек.
Лекция № 10 в курсе "Вычисления на видеокартах" (осень 2018).
Преподаватель курса: Николай Вадимович Полярный
Страница лекции на сайте CS центра: ...

​Google’s 7 steps of Machine Learning in practice: a TensorFlow example for structured data

🔗 Google’s 7 steps of Machine Learning in practice: a TensorFlow example for structured data
A step by step tutorial to put the 7 steps into practice and build a machine learning model from scratch.

​Natural Language Processing Advancements By Deep Learning: A Survey

🔗 Natural Language Processing Advancements By Deep Learning: A Survey
Introduction

​Погружение в Delta Lake: принудительное применение и эволюция схемы

🔗 Погружение в Delta Lake: принудительное применение и эволюция схемы
Привет, Хабр! Представляю вашему вниманию перевод статьи «Diving Into Delta Lake: Schema Enforcement & Evolution» авторов Burak Yavuz, Brenner Heintz and Denny L...

🎥 Lecture #28: One hidden layer Neural Network | Deep Learning
👁 1 раз ⏳ 359 сек.
Complete Course Deep Learning playlist: https://www.youtube.com/playlist?list=PL1w8k37X_6L95W33vEXSE9jXJOfvNB3l8

===============Best Books on Machine Learning :=================
1. Introduction to Machine Learning with Python: A Guide for Data Scientists: https://amzn.to/2TLlhAR
2. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems: https://amzn.to/2wKtPij
3. Pattern Recognition and Machine Learning (Information Science and Stati

🎥 Machine Learning for Asset Managers
👁 1 раз ⏳ 2067 сек.
Convex optimization solutions tend to be unstable, to the point of entirely offsetting the benefits of optimization. For example, in the context of financial applications, it is known that portfolios optimized in sample often underperform the naïve (equal weights) allocation out of sample.

This instability can be traced back to two sources: (1) noise in the input variables; and (2) signal structure that magnifies the estimation errors in the input variables.

There is abundant literature discussing noise i

🎥 Deep Learning - Convolutional Neural Networks Explained
👁 1 раз ⏳ 2756 сек.
Overview of how Convolutional Neural Networks (CNN) perform classification.


This type of Deep Learning is especially well suited working with images. As many of today's scenarios have images as base, CNNs have become one of the most important specializations of Neural Networks.


Instead of extracting features from images in a pre-processing step, CNNs usually work on the raw image data. Through training kernel matrices, they try to find structure and patterns in the image, which are then ultimately usefu

​Визуализация результатов профилирования питона

https://github.com/jiffyclub/snakeviz

🔗 jiffyclub/snakeviz
An in-browser Python profile viewer. Contribute to jiffyclub/snakeviz development by creating an account on GitHub.

​Интерактивные эксперименты по машинному обучению (например, игра в камень-ножницы-бумага с компьютером).

🔗 trekhleb/machine-learning-experiments
🤖 Interactive Machine Learning experiments: 🏋️models training + 🎨models demo - trekhleb/machine-learning-experiments