🎥 Generating Images with Python and PIL for Machine Learning
👁 1 раз ⏳ 635 сек.
Sometimes it can be helpful to generate a large volume of JEPGs or PNGs to create synthetic data for machine learning training. In this video, I demonstrate how I used Python and PIL to create an image recognition dataset for one of my classes.

https://www.kaggle.com/jeffheaton/generate-paperclips

🎥 AWS Live - 1 | AWS Machine Learning Tutorial | Amazon Machine Learning | AWS Training | Edureka
👁 1 раз ⏳ 3698 сек.
🔥AWS Training: https://www.edureka.co/aws-certification-training
This Edureka Live tutorial on ‘AWS Machine Learning Tutorial’ will introduce you to the nitty-gritty of Cloud Computing, Machine Learning and help you build an ML model using AWS.

🔹Amazon AWS Video Tutorial Playlist https://goo.gl/9fQX6J

-----------------------------------------------------------------------------------------
Subscribe to our channel to get video updates. Hit the subscribe button above.

Twitter: https://twitter.com/edurek

🎥 Deep Learning for Imaging Scientists (2020)
👁 3 раз ⏳ 2197 сек.
Hosted by Mike Marsh, Dragonfly Product Manager at ORS
A practical look at Deep Learning for applications in Scientific Imaging.

About this lesson and the Dragonfly Daily
This is lesson 15 in an ongoing daily tutorial series that teaches new users how to become productive with the Dragonfly image processing and visualization platform. This lesson gives users the background details they need in order to work through subsequent lessons in De-noising, Image Segmentation, and Super Resolution, all with Deep Le

​В статье рассматривается создание классификатора изображений.

https://proglib.io/w/70633657

🔗 Image Classification in Data Science
What is image classification in Data Science and building our own image classifier in Python

🎥 Компьютерное зрение и Нейронные сети на Python // День открытых дверей OTUS
👁 1 раз ⏳ 6393 сек.
Трансляция проходила 21 апреля 2020 года

День Открытых Дверей — отличная возможность узнать подробнее о программе курса, особенностях онлайн-формата, навыках, компетенциях и перспективах, которые ждут выпускников после обучения.
Также преподаватель расскажет о своём профессиональном опыте и ответит на вопросы участников.
Поэтому если есть вопрос, запишитесь на онлайн-трансляцию и задайте его в прямом эфире!

Преподаватель: Артур Кадурин - Chief AI Officer Insilico Medicine

Подключайтесь к обсуждению в ч

​Activation Functions: ReLU & Softmax

🔗 Activation Functions: ReLU & Softmax
If you’ve spent some time implementing Deep Learning models, you’ve most likely realized some of the common denominators between any given…

​Einstein, and the Most Beautiful of All Theories

🔗 Einstein, and the Most Beautiful of All Theories
How the General Theory of Relativity Explains the “Anomalous” Precession of the Perihelion of Mercury

​Количественная оценка «эффекта чаши» на томографических изображениях

🔗 Количественная оценка «эффекта чаши» на томографических изображениях
Привет, Хабр! Как вы уже знаете, мы в Smart Engines занимаемся обработкой изображений. Недавно мы написали статью о бинаризации томографических изображений с тон...

​How do Natural Language Processing systems work?

🔗 How do Natural Language Processing systems work?
Have you ever come across situations like you’re typing something on your smartphone and it is coming up with word suggestions based on…

🎥 April 2020 Webinar Accelerating Deep Learning with NVIDIA and Excelero
👁 1 раз ⏳ 3797 сек.
The essence of data-driven sciences such as Deep learning, is the ability to process as much collected and simulated data as possible in the shortest amount of time. GPUs have become the go-to compute resources behind training workloads and NVMe flash has become the standard for high-performance, low latency storage. By providing GPUs with direct access to an elastic pool of NVMe, data scientists and HPC researchers can feed far more data to the applications.

For this second webinar in our 2020 AI webinar

​Chip Design with Deep Reinforcement Learning">
Chip Design with Deep Reinforcement Learning

🔗 Chip Design with Deep Reinforcement Learning
Posted by Anna Goldie, Senior Software Engineer and Azalia Mirhoseini, Senior Research Scientist, Google Research, Brain Team The revolu...

​Understanding Patterns in the Global Economy with Machine Learning

🔗 Understanding Patterns in the Global Economy with Machine Learning
A Hierarchical Clustering Approach

Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

🎥 01.Мотивация
👁 64 раз ⏳ 463 сек.
Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

🎥 02.Компьютерное зрение
👁 37 раз ⏳ 3589 сек.
Вас интересует философия клипового сознания и кинематограф? В этом киноочерке создано движение идей от религиозного характера до научных аргументов. Различные формы передачи информации не только покажут нам особенности клипового мышления, но и подчеркнут его эффектность.

А чтобы лучше понять такую мозаику смыслов вне контекста оригинала, мы увидим цитаты из лекций по логике. Они помогут нам ориентироваться в хаосе клипового сознания. Вы узнаете, как благодаря эволюции человек стал человеком мыслящим. Почему наше мышление устроено как мультимедийный плагиат. Возможно, это и позволило людям так грандиозно развивать технологии на протяжении истории.

🎥 03.Человеческий фактор
👁 3 раз ⏳ 1757 сек.
Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

🎥 04.Социальный интеллект
👁 2 раз ⏳ 3459 сек.
Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

🎥 05.Социальный капитал
👁 1 раз ⏳ 3294 сек.
Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

🎥 06.Самообразование
👁 1 раз ⏳ 2737 сек.
Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

🎥 07.Интуиция
👁 1 раз ⏳ 2379 сек.
Хроники Телевизора: VR XX века / TV Chronicles: XX Century VR

​How is the current state of Big Data Analytics in Controlling?

🔗 How is the current state of Big Data Analytics in Controlling?
Usage and Development in Controlling

🎥 Meetup #AperiTech Online Edition 15/04/2020 - GraphRM - Graph ML + State-driven GraphViz
👁 1 раз ⏳ 4442 сек.
Meetup #AperiTech della Community di GraphRM

Speakers:
- Fischer (Fujitsu Laboratories)
- Wing Au(Fujitsu Laboratories)
"Applying Graph Machine Learning to Enterprise Business Problems"
Jeff Fujitsu’s research labs have worked on graph-based Machine Learning from both a theoretical and an applications perspective. In this talk, we’ll describe Fujitsu’s Deep Tensor technology for graph ML and highlight our experiences with applying graph-ML to business problems.

- Kevin Naughten (Cambridge Intelligence)

​A Gentle Introduction to Degrees of Freedom in Machine Learning - Machine Learning Mastery

🔗 A Gentle Introduction to Degrees of Freedom in Machine Learning - Machine Learning Mastery
Degrees of freedom is an important concept from statistics and engineering. It is often employed to summarize the number of values used in the calculation of a statistic, such as a sample statistic or in a statistical hypothesis test. In machine learning, the degrees of freedom may refer to the number of parameters in the model, such as the number of coefficients

​Training with quantization noise for extreme model compression

Quant-Noise is a new technique to enable extreme compression of models that still deliver high performance when deployed in practical applications.

https://ai.facebook.com/blog/training-with-quantization-noise-for-extreme-model-compression/

Paper: https://arxiv.org/abs/2004.07320

GitHub: https://github.com/pytorch/fairseq/tree/master/examples/quant_noise
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 Training with quantization noise for extreme model compression
Quant-Noise is a new technique to enable extreme compression of state-of-the-art NLP and CV models without significantly affecting performance.

​Batch Normalization In Neural Networks (Code)

🔗 Batch Normalization In Neural Networks (Code)
Implemented With TensorFlow (Keras)

В видео разбирается использование Logistic Regression.

https://www.youtube.com/watch?v=zM4VZR0px8E&feature=youtu.be

🎥 Machine Learning Tutorial Python - 8: Logistic Regression (Binary Classification)
👁 1 раз ⏳ 1159 сек.
Logistic regression is used for classification problems in machine learning. This tutorial will show you how to use sklearn logisticregression class to solve binary classification problem to predict if a customer would buy a life insurance. At the end we have an interesting exercise for you to solve.
Usually there are two types of machine learning problems (1) Linear regression where prediction value is continuous (2) Classification where predicted value is categorical. Logistic regression is used for clas

​Нейросети для детей: объясняем максимально просто

🔗 Нейросети для детей: объясняем максимально просто
Всем привет. Ни для кого не секрет, что практически все статьи в нашем блоге публикуются к запуску того или иного курса. Следующую статью можно было бы приурочит...