​TensorFlow is dead, long live TensorFlow!

https://hackernoon.com/tensorflow-is-dead-long-live-tensorflow-49d3e975cf04

🔗 TensorFlow is dead, long live TensorFlow! - Hacker Noon
If you’re an AI enthusiast and you didn’t see the big news this month, you might have just snoozed through an off-the-charts earthquake…

🎥 Deep Learning @twitter: Twitter meets Tensorflow - Cibele Halasz
👁 1 раз ⏳ 1694 сек.
Twitter has a long story in Machine Learning. Over the past year, we have been transitioning to a new chapter of this story by migrating our ML platform from Lua Torch to Tensorflow. This talk will be focused on the Machine Learning framework we have been developing on top of Tensorflow. Ultimately, we want to give you an idea of how we are doing Machine Learning at Twitter’s scale.
--
Cibele is a Software Engineer at Twitter Cortex, where she builds Twitter’s deep learning platform. Prior to working at Tw

🎥 Friday Seminar Series: Hui Jiang - Understanding Deep Learning Theory
👁 1 раз ⏳ 5240 сек.

🎥 CS480/680 Lecture 15: Deep neural networks
👁 1 раз ⏳ 5466 сек.

🎥 Machine Learning LIVE #1 - Learn Python, Numpy, OpenCV, Pandas & Grab Deep Learning T-Shirt
👁 1 раз ⏳ 3622 сек.
Update - The Submission Link for Pokemon Challenge with Fresh leaderboard will be released tomorrow!
-----------------------------------------------------------------------------------------------------------------------------------------------

Coding Blocks presents you an exclusive webinar on Machine Learning with extensive coverage of Python and Libraries like Numpy, Pandas, Matplotlib, OpenCV. The second part of the webinar will be premiered tomorrow in which you will build the Pokemon Classifier!

A

​Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information

Authors: Evaggelia Tsiligianni, Nikos Deligiannis

Abstract: …the computational complexity. In this paper, we consider the recovery of a target signal with the aid of a correlated signal, the so-called side information (SI), and propose a deep unfolding model that incorporates SI.
https://arxiv.org/abs/1907.02511

🔗 Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information
In linear inverse problems, the goal is to recover a target signal from undersampled, incomplete or noisy linear measurements. Typically, the recovery relies on complex numerical optimization methods; recent approaches perform an unfolding of a numerical algorithm into a neural network form, resulting in a substantial reduction of the computational complexity. In this paper, we consider the recovery of a target signal with the aid of a correlated signal, the so-called side information (SI), and propose a deep unfolding model that incorporates SI. The proposed model is used to learn coupled representations of correlated signals from different modalities, enabling the recovery of multimodal data at a low computational cost. As such, our work introduces the first deep unfolding method with SI, which actually comes from a different modality. We apply our model to reconstruct near-infrared images from undersampled measurements given RGB images as SI. Experimental results demonstrate the superior performance of the

​How We Finished 3rd and Still Won a Data Science Competition

🔗 How We Finished 3rd and Still Won a Data Science Competition
We had a lot of work to do — even after the final scores were published.

This AI Makes The Mona Lisa Come To Life

#DeepFake

🎥 This AI Makes The Mona Lisa Come To Life
👁 1 раз ⏳ 266 сек.
❤️ Check out Weights & Biases here and sign up for a free demo:
https://www.wandb.com/

📝 The paper "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" is available here:
https://arxiv.org/abs/1905.08233v1
https://www.youtube.com/watch?v=p1b5aiTrGzY

🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Bruno Brito, Bryan Learn, Christian Ahlin, Christoph Jad

​Deep Learning Recommendation Model for Personalization and Recommendation Systems:

An implementation of a deep learning recommendation model (DLRM) The model input consists of dense and sparse features. The former is a vector of floating point values. The latter is a list of sparse indices into embedding tables, which consist of vectors of floating point values. The selected vectors are passed to mlp networks denoted by triangles, in some cases the vectors are interacted through operators (Ops).https://github.com/facebookresearch/dlrm

🔗 facebookresearch/dlrm
An implementation of a deep learning recommendation model (DLRM) - facebookresearch/dlrm

​Секция JavaScript: Машинное обучение в JavaScript Библиотеки и решения

🔗 Секция JavaScript: Машинное обучение в JavaScript Библиотеки и решения
Известный факт, что Machine learning - это сфера разработки, которая помогает решать всё большее и большее количество прикладных задач. Но o ML с использованием JavaScript известно пока мало. В докладе я постараюсь раскрыть эту тему. Речь пойдёт об инструментах и возможностях, которыми мы можем пользоваться уже сейчас.

🎥 Свёрточные нейронные сети: dropout, image / data augmentation. Борьба с переобучением.
👁 1 раз ⏳ 881 сек.
⚡⚡⚡ На прошлом уроке мы разработали небольшую свёрточную нейронную сеть для классификации изображений элементов одежды в оттенках серого цвета из набора данных FASHION MNIST. Мы убедились на практике в том, что наша небольшая нейронная сеть может классифицировать поступающие на вход изображения с достаточно высокой точностью. Однако в реальном мире нам предстоит работать с изображениями высокого разрешения и различных размеров. Одним из замечательных преимуществ СНС является тот факт, что они могут так же х

​Дайджест статей машинного обучения и искусственного интеллекта
Программирование,

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Отфильтровав большое количество статей, конференций и подписок — собрал для вас все наиболее значимые гайды, статьи и лайфхаки из мира машинного обучения и искусственного интеллекта. Всем приятного чтения!

1. Проекты искусственного интеллекта, с которыми можно поиграться уже сегодня. Что вы знаете про искусственный интеллект и машинное обучение? Современный тренд или потенциально мощная сила, способная убивать людей? Эти модные понятия всё чаще на слуху, но далеко не все знают, что же это на самом деле. Пришло время изучить эти технологии с помощью простого и интересного подхода — попробовать искусственный интеллект и нейросети самостоятельно на практике.
#DataMining,
#BigData
#Машинноеобучение
#Искусственныйинтеллект
https://habr.com/ru/post/458804/

🔗 Дайджест статей машинного обучения и искусственного интеллекта
Хабр, привет. Отфильтровав большое количество статей, конференций и подписок — собрал для вас все наиболее значимые гайды, статьи и лайфхаки из мира машинного о...

​Generating High-Resolution Images Using Deep Autoregressive Models

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
In this article, I will walk you through the paper and will explain all the terminologies. I have also presented and discussed this work at AISC recently. You can find the full presentation on YouTube.

Before we deep dive into the paper, let me give an overview of what we aim to cover here:

An overview of the paper: its goals and contributions;
A comparison of deep generative models for image generation and recent trends in this area;
An overview of deep autoregressive models for image generation: what they are, why we are interested in them, and major challenges of previous approaches; and
Deep dive into subscale pixel networks and multiscale upscaling: what they are, why they work, and how they compare against previous deep autoregressive models.

🔗 Generating High-Resolution Images Using Autoregressive Models
In this article, I aim to discuss a recent paper from Google Deepmind and Google Brain called “Generating High Fidelity Images With…

🎥 Искусственный интеллект для Instagram бота (машинное обучение, AdaBoost)
👁 1 раз ⏳ 620 сек.
Сделал небольшой искусственный интеллект для Instagram-бота с помощью алгоритма машинного обучения AdaBoost. Бот анализирует информацию об аккаунте и оценивает вероятность того, что человек подпишется в ответ.

Техническая информация:
- Размер обучающего множества: 1106 аккаунтов (597 отрицательных результатов, 509 положительных)
- Слабые классификаторы: плоскости в пространстве (x: follower, y: following, z: x / y)
- Сильный классификатор: комбинация 5 слабых классификаторов дает точность около 84% на обу

​Google football environment — installation and Training RL agent using A3C

🔗 Google football environment — installation and Training RL agent using A3C
Understanding and installation of google football environment. Training A3C algorithm on gfootball.

​Early Detection of Sepsis Using Physiological Data

🔗 Early Detection of Sepsis Using Physiological Data
What is Sepsis ?

🎥 TensorFlow.js Bringing Machine Learning to the Web and Beyond
👁 1 раз ⏳ 1221 сек.
In this video, you will learn about the TensorFlow.js ecosystem: how to bring an existing ML model into your JS app and re-train the model using your data. We’ll also go over our efforts beyond the browser to bring ML to platforms such as React Native, Raspberry Pi, and Electron, and we’ll do a live demo of some of our favorite and unique applications!

Complete Guide to TensorFlow for Deep Learning with Python
☞ http://learnstartup.net/p/BJT8gGKsb

Introducing TensorFlow.js: Machine Learning in Javascript

​Gaining Insights in a Simulated Marketplace with Machine Learning at Uber

#artificialintelligence
https://eng.uber.com/simulated-marketplace/

🔗 Gaining Insights in a Simulated Marketplace with Machine Learning at Uber
Uber's Marketplace simulation platform leverages ML to rapidly prototype and test new product features and hypotheses in a risk-free environment.

Линейная алгебра

Линейная алгебра важна для понимания практически всех технических дисциплин (физика, статистика, Computer Science и т.д.). Из данного видеокурса вы узнаете:

1. Сущность линейной алгебры
2. Что такое вектор?
3. Базовые понятия: линейная комбинация векторов, линейная зависимость векторов и т.д.
4. Линейные преобразования и матрицы
5. Умножение матриц
6. Трехмерные линейные преобразования
7. Детерминант
8. Что такое обратная матрица, ранг матрицы и т.д.
9. Неквадратные матрицы как трансформации между измерениями
10. Скалярные произведения и дуальность

🎥 Essence of linear algebra preview
👁 1 раз ⏳ 305 сек.
This introduces the "Essence of linear algebra" series, aimed at animating the geometric intuitions underlying many of the topics taught in a stand...

🎥 Vectors, what even are they? | Essence of linear algebra, chapter 1
👁 1 раз ⏳ 592 сек.
I imagine many viewers are already familiar with vectors in some context, so this video is intended both as a quick review of vector terminology, a...

🎥 Linear combinations, span, and basis vectors | Essence of linear algebra, chapter 2
👁 1 раз ⏳ 599 сек.
The fundamental vector concepts of span, linear combinations, linear dependence, and bases all center on one surprisingly important operation: Scal...

🎥 Linear transformations and matrices | Essence of linear algebra, chapter 3
👁 1 раз ⏳ 659 сек.
Matrices can be thought of as transforming space, and understanding how this work is crucial for understanding many other ideas that follow in line...

🎥 Matrix multiplication as composition | Essence of linear algebra, chapter 4
👁 1 раз ⏳ 604 сек.
Multiplying two matrices represents applying one transformation after another. Many facts about matrix multiplication become much clearer once you...

🎥 Three-dimensional linear transformations | Essence of linear algebra, footnote
👁 1 раз ⏳ 286 сек.
What do 3d linear transformations look like? Having talked about the relationship between matrices and transformations in the last two videos, thi...

🎥 The determinant | Essence of linear algebra, chapter 5
👁 1 раз ⏳ 603 сек.
The determinant of a linear transformation measures how much areas/volumes change during the transformation.

Watch the full "Essence of linear alg...

🎥 Inverse matrices, column space and null space | Essence of linear algebra, chapter 6
👁 1 раз ⏳ 729 сек.
How to think about linear systems of equations geometrically. The focus here is on gaining an intuition for the concepts of inverse matrices, colu...

🎥 Nonsquare matrices as transformations between dimensions | Essence of linear algebra, footnote
👁 1 раз ⏳ 267 сек.
Because people asked, this is a video briefly showing the geometric interpretation of non-square matrices as linear transformations that go between...

🎥 Dot products and duality | Essence of linear algebra, chapter 7
👁 1 раз ⏳ 852 сек.
Dot products are a nice geometric tool for understanding projection. But now that we know about linear transformations, we can get a deeper feel f...

​Attention для чайников и реализация в #Keras
#Python

Не смотря на то что механизм Attention описан в англоязычной литературе, в русскоязычном секторе достойного описание данной технологии я до сих пор не встречал. На нашем языке есть много статей по Искусственному Интеллекту (ИИ). Тем не менее, те статьи, которые удалось найти, раскрывают только самые простые модели ИИ, например, свёрточные сети, генеративные сети. Однако, по передовым новейшим разработками в области ИИ статей в русскоязычном секторе крайне мало.
https://habr.com/ru/post/458992/

🔗 Attention для чайников и реализация в Keras
О статьях по искусственному интеллекту на русском языке Не смотря на то что механизм Attention описан в англоязычной литературе, в русскоязычном секторе достойн...

​Slim-CNN: A Light-Weight CNN for Face Attribute Prediction. arxiv.org/abs/1907.02157

🔗 Slim-CNN: A Light-Weight CNN for Face Attribute Prediction
We introduce a computationally-efficient CNN micro-architecture Slim Module to design a lightweight deep neural network Slim-Net for face attribute prediction. Slim Modules are constructed by assembling depthwise separable convolutions with pointwise convolution to produce a computationally efficient module. The problem of facial attribute prediction is challenging because of the large variations in pose, background, illumination, and dataset imbalance. We stack these Slim Modules to devise a compact CNN which still maintains very high accuracy. Additionally, the neural network has a very low memory footprint which makes it suitable for mobile and embedded applications. Experiments on the CelebA dataset show that Slim-Net achieves an accuracy of 91.24% with at least 25 times fewer parameters than comparably performing methods, which reduces the memory storage requirement of Slim-net by at least 87%.