​Word Vectors and Lexical Semantics (Part 1)

🔗 Word Vectors and Lexical Semantics (Part 1)
The following are my personal notes based on the Deep NLP course by Oxford University held in 2017. The material is available at [1].

​Training deep neural networks on a GPU with PyTorch

🔗 Training deep neural networks on a GPU with PyTorch
Part 4 of “PyTorch: Zero to GANs”

​How to correctly select a sample from a huge dataset in machine learning

🔗 How to correctly select a sample from a huge dataset in machine learning
Choosing a small, representative dataset from a large population can improve model training reliability

​Monte Carlo Integration is Magic

🔗 Monte Carlo Integration is Magic
How to compute an integral in 3 lines of code

​Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
https://www.shortscience.org/paper?bibtexKey=journals/corr/1406.4729

🔗 Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition - ShortScience.org
Spatial Pyramid Pooling (SPP) is a technique which allows Convolutional Neural Networks (CNNs) to use input images of any size, not only $224\text{px} \times 224\text{px}$ as most architectures do. (However, there is a lower bound for the size of the input image). ## Idea * Convolutional layers operate on any size, but fully connected layers need fixed-size inputs * Solution: * Add a new SPP layer on top of the last convolutional layer, before the fully connected layer * Use an approach similar to bag of words (BoW), but maintain the spatial information. The BoW approach is used for text classification, where the order of the words is discarded and only the number of occurences is kept. * The SPP layer operates on each feature map independently. * The output of the SPP layer is of dimension $k \cdot M$, where $k$ is the number of feature maps the SPP layer got as input and $M$ is the number of bins. Example: We could use spatial pyramid pooling with

🎥 Михаил Цветков: «Обзор проектов Intel в области машинного обучения и систем AI»
👁 6 раз ⏳ 3342 сек.
Доклад «Обзор проектов Intel в области машинного обучения и систем AI: новые аппаратные платформы и оптимизация на программном уровне» будет читать Михаил Цветков, лидер технической группы Intel в России. Михаил закончил Физический факультет и аспирантуру по направлению Физика полупроводниковых приборов и микроэлектроника Воронежского Университета. Работал в подразделениях Intel Labs и Intel Architecture Group в Intel с 2008 года. Специализация — разработка пространственных структур обработки данных на FPGA

🎥 Машинное обучение на реальных кейсах
👁 1 раз ⏳ 5198 сек.
Спикер Андрей Латыш, инженер по машинному обучению анализу данных в The Product Engine.

Программа:
- история машинного обучения;
- суть машинного обучения;
- распространенные алгоритмы с демонстрацией и объяснением на практических, бизнес-примерах.

Компьютерная Школа Hillel

site: https://ithillel.ua
тел.: +38 (097) 156-58-27

fb: https://www.facebook.com/hillel.it.school
in: https://www.instagram.com/hillel_itschool
tw: https://twitter.com/hillel_itschool
ln: https://www.linkedin.com/company/hillel_itsch

https://www.youtube.com/watch?v=Ejsr3S79gcQ/

🎥 Байесовские методы в машинном обучении. Лекция 1
👁 1 раз ⏳ 5449 сек.
Лектор: профессор Ветров Дмитрий Петрович

🎥 Google Cloud Next, Machine Learning, & more! (This Week in Cloud)
👁 1 раз ⏳ 141 сек.
Here to bring you the latest news in the cloud is Google Cloud Developer Advocate Stephanie Wong.

Learn more about these announcements → https://bit.ly/2TqGuME

• Weekly updates (blog) → https://bit.ly/2TmTgvS
• Get Cloud Certified → https://bit.ly/2Tqmwlh
• TensorFlow Deep Learning VM Instances → https://bit.ly/2Toph6Q
• G Suite Updates → https://bit.ly/2TqHHUc

This Week in The Cloud is a new series where we serve you the lowest latency news → https://bit.ly/ThisWeek-inCloud

Tune in every week for a n

🎥 Stanford CS230: Deep Learning | Autumn 2018 | Lecture 3 - Full-Cycle Deep Learning Projects
👁 1 раз ⏳ 4697 сек.
Andrew Ng, Adjunct Professor & Kian Katanforoosh, Lecturer - Stanford University
http://onlinehub.stanford.edu/

Andrew Ng
Adjunct Professor, Computer Science

Kian Katanforoosh
Lecturer, Computer Science

To follow along with the course schedule and syllabus, visit:
http://cs230.stanford.edu/

To get the latest news on Stanford’s upcoming professional programs in Artificial Intelligence, visit: http://learn.stanford.edu/AI.html

To view all online courses and programs offered by Stanford, visit: http:

🎥 Stanford CS230: Deep Learning | Autumn 2018 | Lecture 2 - Deep Learning Intuition
👁 1 раз ⏳ 4967 сек.
Andrew Ng, Adjunct Professor & Kian Katanforoosh, Lecturer - Stanford University
http://onlinehub.stanford.edu/

Andrew Ng
Adjunct Professor, Computer Science

Kian Katanforoosh
Lecturer, Computer Science

To follow along with the course schedule and syllabus, visit:
http://cs230.stanford.edu/

To get the latest news on Stanford’s upcoming professional programs in Artificial Intelligence, visit: http://learn.stanford.edu/AI.html

To view all online courses and programs offered by Stanford, visit: http:

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🎥 Евгений Борисов: «Настоящие и будущие супер-решения Supermicro для систем ИИ и анализа данных»
👁 1 раз ⏳ 4546 сек.
Продукция компании Supermicro — производителя серверных платформ — является ключевым звеном в цепи «превращения умных чипов в законченные функциональные устройства». Она применяется в крупных дата-центрах и в первую очередь — в ЦОДах, ориентированных на системы искусственного интеллекта (AI/ML/DL).

Практическая аппаратная часть систем искусственного интеллекта для решений конкретных задач начинается с серверных платформ. В Supermicro-платформы устанавливаются «ИИ-акселераторы» разной функциональности: CPU,

🎥 Байесовские методы в машинном обучении. Лекция 6
👁 1 раз ⏳ 5159 сек.
Лектор: профессор Ветров Дмитрий Петрович

🎥 Байесовские методы в машинном обучении. Лекция 5
👁 1 раз ⏳ 4723 сек.
Лектор: профессор Ветров Дмитрий Петрович

🎥 Байесовские методы в машинном обучении. Лекция 4
👁 1 раз ⏳ 5100 сек.
Лектор: профессор Ветров Дмитрий Петрович

🎥 Байесовские методы в машинном обучении. Лекция 3
👁 1 раз ⏳ 4232 сек.
Лектор: профессор Ветров Дмитрий Петрович

​Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks

🔗 Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks
For this tutorial in my Reinforcement Learning series, we are going to be exploring a family of RL algorithms called Q-Learning algorithms…

​https://arxiv.org/abs/1903.06048

🔗 MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis
While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to use, in part due to instability during training. One commonly accepted reason for this instability is that gradients passing from the discriminator to the generator can quickly become uninformative, due to a learning imbalance during training. In this work, we propose the Multi-Scale Gradient Generative Adversarial Network (MSG-GAN), a simple but effective technique for addressing this problem which allows the flow of gradients from the discriminator to the generator at multiple scales. This technique provides a stable approach for generating synchronized multi-scale images. We present a very intuitive implementation of the mathematical MSG-GAN framework which uses the concatenation operation in the discriminator computations. We empirically validate the effect of our MSG-GAN approach through experiments on the CIFAR10 and Oxford102 flowers datasets and compare it with other relevant techniques which perform multi-scale image synthesis. In addition, we also provide details of our experiment on CelebA-HQ dataset for synthesizing 1024 x 1024 high resolution images.

​Автоматизация ответов на часто задаваемые вопросы в навыке для «Алисы» с помощью библиотеки DeepPavlov

Наш телеграм канал - tglink.me/ai_machinelearning_big_data

https://habr.com/ru/company/mipt/blog/445748/

🔗 Автоматизация ответов на часто задаваемые вопросы в навыке для «Алисы» с помощью библиотеки DeepPavl
Лаборатория нейронных систем и глубокого обучения МФТИ вот уже больше года делает DeepPavlov — открытую библиотеку для создания диалоговых систем. Она содержит н...

🎥 Robotics navigation with Intel® RealSense™ Tracking Camera T265 and Depth Camera D435
👁 1 раз ⏳ 114 сек.
Robotics Navigation – In this video, we show a prototype demo of the Intel® RealSense™ Depth Camera D435 and the Intel® RealSense™ Tracking Camera T265 being used for V-SLAM, occupancy mapping, path planning and collision avoidance. We will be releasing some of the code used in this demo in the near future on our github at https://github.com/IntelRealSense/librealsense

More information on the cameras –
https://realsense.intel.com/depth-camera/#D415_D435
https://realsense.intel.com/tracking-came