🎥 Задание графов исполнения в распределенных системах
👁 1 раз ⏳ 2429 сек.
Существующие фреймворки распределенной обработки данных предоставляют пользователю возможность в различной степени влиять на построение плана исполнения. Ограничения могут возникать как из-за особенностей физической реализации распределенной системы, так и из-за принимаемой модели и вычислительной парадигмы.

На семинаре будут рассмотрены существующие подходы к заданию вычислений, начиная с MapReduce и заканчивая декларативными языками.

Докладчик: Вадим Фарутин.

Ссылка на слайды: https://research.jetbrain

​Advanced Machine Learning Day 3: Neural Architecture Search

🔗 Advanced Machine Learning Day 3: Neural Architecture Search
How do you search over architectures? View presentation slides and more at https://www.microsoft.com/en-us/research/video/advanced-machine-learning-day-3-neural-architecture-search/

​Democratising Machine learning with H2O

🔗 Democratising Machine learning with H2O
It is important to make AI accessible to everyone for the sake of social and economic stability.

​A Gentle Introduction to Channels First and Channels Last Image Formats for Deep Learning

🔗 A Gentle Introduction to Channels First and Channels Last Image Formats for Deep Learning
Color images have height, width, and color channel dimensions. When represented as three-dimensional arrays, the channel dimension for the image data is last by default, but may be moved to be the first dimension, often for performance-tuning reasons. The use of these two “channel ordering formats” and preparing data to meet a specific preferred channel …

​http://arxiv.org/abs/1904.08410

🔗 Neural Painters: A learned differentiable constraint for generating brushstroke paintings
We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encouraging this agent to follow human-like strokes when reconstructing digits. We also explore the use of a neural painter as a differentiable image parameterization. By directly optimizing brushstrokes to activate neurons in a pre-trained convolutional network, we can directly visualize ImageNet categories and generate "ideal" paintings of each class. Finally, we present a new concept called intrinsic style transfer. By minimizing only the content loss from neural style transfer, we allow the artistic medium, in this case, brushstrokes, to naturally dictate the resulting style.

​ChengBinJin/MRI-to-CT-DCNN-TensorFlow

🔗 ChengBinJin/MRI-to-CT-DCNN-TensorFlow
This repository is the implementations of the paper "MR-based Synthetic CT Generation using Deep Convolutional Neural Network Method," Medical Physics 2017. - ChengBinJin/MRI-to-CT-DCNN-T...

​Пишу от команды CatBoost. Мы очень хотим сделать CatBoost лучшим градиентным бустингом в мире. Помогите нам, ответьте на вопросы в небольшом опросе по ссылке, чтобы мы лучше понимали, что важно для пользователей градиентного бустинга: https://forms.yandex.ru/surveys/10011699/?lang=en. Также ссылка на опрос есть у нас на сайте https://catboost.ai

🔗 Gradient Boosting Survey — Yandex.Forms

​https://arxiv.org/abs/1904.01326

🔗 HoloGAN: Unsupervised learning of 3D representations from natural images
We propose a novel generative adversarial network (GAN) for the task of unsupervised learning of 3D representations from natural images. Most generative models rely on 2D kernels to generate images and make few assumptions about the 3D world. These models therefore tend to create blurry images or artefacts in tasks that require a strong 3D understanding, such as novel-view synthesis. HoloGAN instead learns a 3D representation of the world, and to render this representation in a realistic manner. Unlike other GANs, HoloGAN provides explicit control over the pose of generated objects through rigid-body transformations of the learnt 3D features. Our experiments show that using explicit 3D features enables HoloGAN to disentangle 3D pose and identity, which is further decomposed into shape and appearance, while still being able to generate images with similar or higher visual quality than other generative models. HoloGAN can be trained end-to-end from unlabelled 2D images only. Particularly, we do not require pose labels, 3D shapes, or multiple views of the same objects. This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.

🎥 Stanford CS230: Deep Learning | Autumn 2018 | Lecture 1 - Class Introduction and Logistics
👁 1 раз ⏳ 4072 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 10
👁 1 раз ⏳ 3292 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 7
👁 1 раз ⏳ 5698 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 6
👁 1 раз ⏳ 3024 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 9
👁 1 раз ⏳ 4820 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 8
👁 1 раз ⏳ 3888 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:

​3Q: Setting academic parameters for the MIT Schwarzman College of Computing

🔗 3Q: Setting academic parameters for the MIT Schwarzman College of Computing
Working Group on Curricula and Degrees co-chairs discuss their progress toward establishing credentials and courses for the college.

​Difference between Batch Gradient Descent and Stochastic Gradient Descent

🔗 Difference between Batch Gradient Descent and Stochastic Gradient Descent
[WARNING: TOO EASY!]

​Pandas in the Premier League

🔗 Pandas in the Premier League
How can we get started with Pandas for Data Analysis

🎥 Watch Me Build a Marketing Startup
👁 1 раз ⏳ 2751 сек.
I've built an app called VectorFunnel that automatically scores leads for marketing & sales teams! I used React for the frontend, Node.js for the backend, PostgreSQL for the database, and Tensorflow.js for scoring each lead in an excel spreadsheet. There are a host of other tools that I used like ClearBit's data API and various Javascript frameworks. If you have no idea what any of that is, that's ok I'll show you! In this video, I'll explain how I built the app so that you can understand how all these part

​CS294-158 Deep Unsupervised Learning SP19

🔗 CS294-158 Deep Unsupervised Learning SP19

​Applied Machine Learning 2019 - Lecture 22 - Advanced Neural Networks

🔗 Applied Machine Learning 2019 - Lecture 22 - Advanced Neural Networks
Residual Networks, DenseNet, Recurrent Neural Networks. Slides and materials on the course website: https://www.cs.columbia.edu/~amueller/comsw4995s19/schedule/