​A Gentle Introduction to Convolutional Layers for Deep Learning Neural Networks

🔗 A Gentle Introduction to Convolutional Layers for Deep Learning Neural Networks
Convolution and the convolutional layer are the major building blocks used in convolutional neural networks. A convolution is the simple application of a filter to an input that results in an activation. Repeated application of the same filter to an input results in a map of activations called a feature map, indicating the locations and …

​[Открытые лекции]: Машинное обучение для фундаментальных исследований

🔗 [Открытые лекции]: Машинное обучение для фундаментальных исследований
Денис Деркач, доцент департамента больших данных и информационного поиска Применение методов машинного обучения стало необходимым этапом анализа данных в физ...

​MD vs. Machine: Artificial intelligence in health care

🔗 MD vs. Machine: Artificial intelligence in health care
Recent advances in artificial intelligence and machine learning are changing the way doctors practice medicine. Can medical data actually improve health care...

​Smart Farming: Mixed Reality and AI

🔗 Smart Farming: Mixed Reality and AI
Mixed reality (MR) and artificial intelligence (AI) can enhance the output and efficiency of farms. Here’s how.

🎥 Видео открытого урока курса "Big Data для менеджеров" от CleverDATA и OTUS.
👁 1 раз ⏳ 4462 сек.
Артем Просветов (Art Prosvetov), руководитель практики анализа данных и машинного интеллекта в CleverDATA, рассказывает о базовых принципах анализа данных для аудитории без предварительной подготовки. Слушатели познакомятся с несколькими инструментами анализа данных, такими как статистические тесты, предсказательная модель Random Forest и тематическое моделирование для работы с текстовыми данными.

-
Сегодня в дефиците не только технические специалисты, способные организовать работу с данными, но и менеджер

​Машинное обучение без Python, Anaconda и прочих пресмыкающихся

Нет, ну я, конечно, не всерьез. Должен же быть предел, до какой степени возможно упрощать предмет. Но для первых этапов, понимания базовых концепций и быстрого «въезжания» в тему, может быть, и допустимо. А как правильно поименовать данный материал (варианты: «Машинное обучение для чайников», «Анализ данных с пеленок», «Алгоритмы для самых маленьких»), обсудим в конце.

К делу. Написал несколько прикладных программ на MS Excel для визуализации и наглядного представления процессов, которые происходят в разных методах машинного обучения при анализе данных. Seeing is believing, в конце концов, как говорят носители культуры, которая и разработала большинство этих методов (кстати, далеко не все. Мощнейший «метод опорных векторов», или SVM, support vector machine – изобретение нашего соотечественника Владимира Вапника, Московский Институт управления. 1963 год, между прочим! Сейчас он, правда, преподает и работает в США).
https://habr.com/ru/post/446150/

🔗 Машинное обучение без Python, Anaconda и прочих пресмыкающихся
Нет, ну я, конечно, не всерьез. Должен же быть предел, до какой степени возможно упрощать предмет. Но для первых этапов, понимания базовых концепций и быстрого «...

​Facebook AI Research singing voice conversion

🔗 Facebook AI Research singing voice conversion

​Making the Mueller Report Searchable with OCR and Elasticsearch

🔗 Making the Mueller Report Searchable with OCR and Elasticsearch
April 18th marked the full release of the Mueller Report — a document outlining the investigation of potential Russian interference in the…

​https://builders.intel.com/

🔗 Intel® Builders - Programs for Network Transformation Data Center
Intel® Builder programs drive to data innovation, improve solution fulfill customer requirement with high-speed data deployment and reliability of data center.

​ScaledML 2019 - YouTube

🔗 ScaledML 2019 - YouTube
Scaled Machine Learning Conference 2019

​Google Colaboratory

🔗 Google Colaboratory

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data

https://towardsdatascience.com/when-clustering-doesnt-make-sense-c6ed9a89e9e6?source=collection_home---4------0---------------------

🔗 When Clustering Doesn’t Make Sense
A few things to consider before clustering your data

​MorphNet: Towards Faster and Smaller Neural Networks
Наш телеграм канал - tglink.me/ai_machinelearning_big_data

http://ai.googleblog.com/2019/04/morphnet-towards-faster-and-smaller.html

🔗 MorphNet: Towards Faster and Smaller Neural Networks
Posted by Andrew Poon, Senior Software Engineer and Dhyanesh Narayanan, Product Manager, Google AI Perception Deep neural networks (DNNs...

🎥 Principles and applications of relational inductive biases in deep learning
👁 1 раз ⏳ 2207 сек.
Kelsey Allen, MIT

Common intuition posits that deep learning has succeeded because of its ability to assume very little structure in the data it receives, instead learning that structure from large numbers of training examples. However, recent work has attempted to bring structure back into deep learning, via a new set of models known as "graph networks". Graph networks allow for "relational inductive biases" to be introduced into learning, ie. explicit reasoning about relationships between entities. In th

🎥 Deep Learning Interview Questions and Answers | AI & Deep Learning Interview Questions | Edureka
👁 25 раз ⏳ 2442 сек.
*** AI and Deep-Learning with TensorFlow - https://www.edureka.co/ai-deep-learning-with-tensorflow ***
This video covers most of the hottest deep learning interview questions and answers. It also provides you with an understanding process of Deep Learning and the various aspects of it.

#edureka #DeepLearningInterviewQuestions #TensorFlowInterviewQuestions #DeepLearning #TensorFlow
-------------------------------------------------

*** Machine Learning Podcast - https://castbox.fm/channel/id1832236 ***
In

​Deep learning models reveal internal structure and diverse computations in the retina under natural scenes

🔗 Deep learning models reveal internal structure and diverse computations in the retina under natural scenes
The normal function of the retina is to convey information about natural visual images. It is this visual environment that has driven evolution, and that is clinically relevant. Yet nearly all of our understanding of the neural computations, biological function, and circuit mechanisms of the retina comes in the context of artificially structured stimuli such as flashing spots, moving bars and white noise. It is fundamentally unclear how these artificial stimuli are related to circuit processes engaged under natural stimuli. A key barrier is the lack of methods for analyzing retinal responses to natural images. We addressed both these issues by applying convolutional neural network models (CNNs) to capture retinal responses to natural scenes. We find that CNN models predict natural scene responses with high accuracy, achieving performance close to the fundamental limits of predictability set by intrinsic cellular variability. Furthermore, individual internal units of the model are highly correlated with actual retinal interneuron responses that were recorded separately and never presented to the model during training. Finally, we find that models fit only to natural scenes, but not white noise, reproduce a range of phenomena previously described using distinct artificial stimuli, including frequency doubling, latency encoding, motion anticipation, fast contrast adaptation, synchronized responses to motion reversal and object motion sensitivity. Further examination of the model revealed extremely rapid context dependence of retinal feature sensitivity under natural scenes using an analysis not feasible from direct examination of retinal responses. Overall, these results show that nonlinear retinal processes engaged by artificial stimuli are also engaged in and relevant to natural visual processing, and that CNN models form a powerful and unifying tool to study how sensory circuitry produces computations in a natural context.

​План ИИ-трансформации: как управлять компанией в эпоху ИИ?

🔗 План ИИ-трансформации: как управлять компанией в эпоху ИИ?
Делимся с вами ещё одним полезным переводом статьи. Также всех, у кого есть желание за 3 месяца освоить Best Practice по внедрению в проекты современных аналитич...

​Microsoft Introduction to AI — Part 3

🔗 Microsoft Introduction to AI — Part 3
Computer Vision

​How Do Neural Networks Memorize Text?

🔗 How Do Neural Networks Memorize Text?
📝 The paper "Visualizing memorization in RNNs" is available here: https://distill.pub/2019/memorization-in-rnns/ ❤️ Pick up cool perks on our Patreon page: h...

​How I used Python to analyze Game of Thrones

🔗 How I used Python to analyze Game of Thrones
I wanted to learn Python. When I had to do a bunch of boring stuff for work… I got my chance! I will now show you, using Game of Thrones!